JP7482200B1 - Determination device, determination method, and determination program - Google Patents

Abstract

[Problem] To improve the accuracy of pricing used goods. [Solution] A determination device according to the present application includes an estimation unit and a determination unit. The estimation unit estimates the current probability of an immediate sale of a target item based on the current target listing price of the target item and an immediate sale probability estimation model that estimates the immediate sale probability of the target item. The determination unit determines the listing price of the target item according to the immediate sale probability estimated by the estimation unit. [Selected Figure] Figure 11

Description

The present invention relates to a determination device, a determination method, and a determination program.

When selling second-hand goods, there were cases where the profit that should have been made was lost due to listing the goods at a price lower than the market price. In particular, with a pricing model in which the price is set on the day of purchase, it is difficult to predict whether the price will rise, and so the price may end up being too low. For example, since second-hand goods tend to fall in price gradually, if the price drops slightly, it may be predicted that the price will continue to decline, and the price may end up being too low, even if the item is actually worth more than the market price.

Conventionally, there are known technologies that support the purchase of second-hand goods. For example, a technology is known that calculates the supply and demand balance in the market based on the distribution status of the goods and determines the appropriate selling price of the second-hand goods (Patent Document 1 below). Also, a technology is known that calculates the selection probability of a product and adjusts the selling price according to the selection probability (Patent Document 2 below).

JP 2001-134635 A International Publication No. 2021/039916

However, conventional technology has not been able to appropriately determine a fair price for selling used goods. For example, conventional technology has not been able to appropriately determine a fair price for selling that takes into account the possibility of an item being sold on the same day it is put up for sale.

This application was made in light of the above, and aims to improve the accuracy of pricing used goods.

The determination device according to the present application is characterized by having an estimation unit that estimates the current probability of an immediate sale of a target product based on the current target listing price of the target product and an immediate sale probability estimation model that estimates the immediate sale probability of the target product, and a determination unit that determines the listing price of the target product according to the immediate sale probability estimated by the estimation unit.

According to one aspect of the embodiment, it is possible to improve the accuracy of pricing used items.

FIG. 1 is a diagram illustrating an example of the configuration of a determination system according to an embodiment. FIG. 2 is a diagram illustrating an example of a determination process according to the embodiment. FIG. 3 is a diagram illustrating an example of the configuration of a user terminal according to the embodiment. FIG. 4 is a diagram illustrating an example of the configuration of a determination device according to an embodiment. FIG. 5 is a diagram illustrating an example of a storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a storage unit according to the embodiment. FIG. 7 is a flowchart illustrating an example of a determination process according to the embodiment. FIG. 8 is a diagram illustrating an example of the configuration of a determination system according to the second embodiment. FIG. 9 is a diagram illustrating an example of a determination process according to the second embodiment. FIG. 10 is a diagram illustrating an example of the configuration of a carrier terminal according to the second embodiment. FIG. 11 is a diagram illustrating an example of the configuration of a determination device according to the second embodiment. FIG. 12 is a diagram illustrating an example of a sales price storage unit according to the second embodiment. FIG. 13 is a diagram illustrating an example of an immediate sales result storage unit according to the second embodiment. FIG. 14 is a flowchart illustrating an example of a determination process according to the second embodiment. FIG. 15 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the determination device.

Below, a detailed description will be given of a form for implementing the determination device, determination method, and determination program of the present application (hereinafter, referred to as an "embodiment") with reference to the drawings. Note that the determination device, determination method, and determination program of the present application are not limited to this embodiment. Also, the same parts in each of the following embodiments are given the same reference numerals, and duplicated descriptions will be omitted.

1. Embodiment 1
1-1. Configuration of the decision system
A determination system 1 shown in Fig. 1 will be described. As shown in Fig. 1, the determination system 1 includes a user terminal 10 and a determination device 100. The user terminal 10 and the determination device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other by wire or wirelessly. Fig. 1 is a diagram showing an example of the configuration of the determination system 1 according to the embodiment.

The user terminal 10 is an information processing device used by a user who is requesting a purchase and giving up their property. The user terminal 10 may be any device that can realize the processing in the embodiment. The user terminal 10 may also be a device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. Figure 2 shows the case where the user terminal 10 is a smartphone.

The user terminal 10 is, for example, a smart device such as a smartphone or tablet, and is a mobile terminal device that can communicate with any server device via a wireless communication network such as 3G to 5G (Generation) or LTE (Long Term Evolution). The user terminal 10 also has a screen such as a liquid crystal display with touch panel functionality, and may accept various operations on displayed data such as content, such as tapping, sliding, scrolling, etc., performed by a user's finger or stylus. In FIG. 2, the user terminal 10 is used by a user U11.

The determination device 100 is an information processing device intended to improve the accuracy of pricing used goods, and may be any device capable of implementing the processing in the embodiment. The determination device 100 is realized, for example, by a server device or a cloud system. For example, the determination device 100 is realized by a server device or a cloud system of a specified service that buys and sells used goods.

1-2. An example of the decision process
2 is a diagram illustrating an example of a determination process of the determination system 1 according to the embodiment. In the following embodiment, a description will be given using used clothes as an example of a product to be purchased.

First, let us explain how used clothing is priced. Generally, when buying used clothing, the clothes sent in do not come with price tags, and therefore do not come with a code that can identify the individual item, such as a JAN code. Also, while some items can be identified individually by searching for the brand's unique model number included on the quality label, checking and searching for each low- to mid-priced used item is time-consuming and may not be realistic in terms of cost.

In addition, a common method of pricing used clothing is to treat all items as single items without taking into account the existence of items with the same model number, and to set prices using a price table based on at least one combination of brand, category, and condition. However, this method cannot reflect, for example, recent sales performance by model number or depreciation in value in the price, and can result in low pricing accuracy.

In order to improve the accuracy of pricing, the model number of a new product of the same item in a specific online shopping mall is determined in advance, and the model number is linked to used product information and new product information.

In the following embodiment, it is assumed that a user U11 who requests purchase has requested the purchase of used clothing P11. Specifically, it is assumed that information for requesting the purchase of used clothing P11 is transmitted from the user terminal 10 to the decision device 100 by an operation by the user U11.

The determination device 100 acquires information for requesting the purchase of the used clothing P11 sent from the user terminal 10 (step S101). Then, based on the information for requesting the purchase of the used clothing P11, the determination device 100 acquires, for example, business information of a specified service for which the purchase of the used clothing P11 has been requested, and business information of a specified online shopping mall where the user U11 has purchased a new item of the same product.

(Based on purchase history)
Based on the acquired information, the determination device 100 determines whether the specified service requested to purchase the used clothes P11 has a specified relationship (for example, the same business operator) with the specified online shopping mall where the user U11 purchased a new product of the same product. If the determination device 100 determines that the specified service requested to purchase the used clothes P11 has a specified relationship with the specified online shopping mall where the user U11 purchased a new product of the same product, it acquires the purchase history of the specified online shopping mall that is determined to have the specified relationship, and identifies the model number of the new product of the same product in the specified online shopping mall that is determined to have the specified relationship based on the acquired purchase history (step S102). For example, this is the case when the user U11 requests the purchase of the used clothes P11 through the specified online shopping mall where the user U11 purchased the new product.

(Identification based on tag information)
Furthermore, when the determination device 100 determines that the specific service for which the purchase of the used clothing P11 is requested does not have a specific relationship with the specific online shopping mall where the user U11 purchased a new product of the same product, it identifies the model number of a new product of the same product in the specific online shopping mall that has a specific relationship with the specific service for which the purchase of the used clothing P11 is requested, for example, based on tag information (e.g., information on the brand's unique model number included in the quality display tag) attached to the used clothing P11 sent to the store of the specific service for which the purchase is requested. For example, this is the case when the used clothing P11 was purchased in a specific online shopping mall that does not have a specific relationship with the specific service for which the purchase is requested.

(Model Generation)
The determination device 100 generates a model that outputs a price (sales price) that is a basis for calculating an estimated price for the sale of a used item for each condition of the used item based on the new product information and used product information of the product with a sales record (step S103). For example, the determination device 100 generates a model based on XGBoost (eXtreme Gradient Boosting) or the like, using the new product information of the product with a sales record and the used product information up to the time of the previous sale as explanatory variables, and the previous sales price as a target variable. Here, the new product information includes, for example, the normal price (initial list price when sold as a new item) of a new item identical to the used clothing P11, the time of start of sales, brand, category, etc. In addition, the used product information includes, for example, the sales price of a used item sold in the past of the same item, the discount rate at the time of sale, the increase or decrease in the sales price, the period from listing to sale (for example, the number of days elapsed), the purchase (trade-in) price, the purchase (trade-in) year, etc. Among these, the used product information includes information on the period from listing to sale.

Here, the selling price may be reversed. For example, suppose that there are condition ranks (S, A, B, C, D) and the standard condition is condition rank (B). Also, suppose that the selling price of the condition rank (C) is higher than the selling price of the higher rank (B), causing a reversal. In this case, the determination device 100 trains the model using the selling price of the condition rank (B) as a positive example, but in reality, the selling price of the condition rank (B) may be incorrect. In this way, when the selling price is reversed, it is not possible to determine whether the selling price of the condition rank (B) or the selling price of the condition rank (C) is actually incorrect. Therefore, if the used item information, which is the input information for the model, does not include information on the period from listing to sale, when such a reversal of the selling price occurs, the selling price of each condition cannot be corrected so that it converges to the appropriate selling price.

On the other hand, if the used item information, which is the input information for the model, includes information on the period from listing to sale, when the selling price is reversed, one of the periods from listing to sale will be very short (even though rank (B) is a higher rank, it sells quickly because its selling price is low), so even if the selling price of the rank (B) condition is actually incorrect, the selling prices of each condition can be corrected to converge to the correct selling price.

The determination device 100 acquires new product information and used product information that are predetermined and linked to the model number of the new product identified based on the purchase history or tag information (step S104). In FIG. 2, the determination device 100 acquires new product information and used product information transmitted from an information providing device 200 that manages a specific online shopping mall Q11. The determination device 100 then inputs the acquired new product information and used product information into the generated model, thereby calculating the selling price for each condition of the used product (step S105). At this time, the model outputs the selling price for each condition according to the used product information for each condition.

Then, the determination device 100 calculates an estimated price for the sale of each condition by multiplying the calculated selling price for each condition by a correction coefficient (step S106). For example, the determination device 100 calculates an estimated price for the sale of each condition by multiplying the selling price for each condition by the same correction coefficient. For example, the determination device 100 calculates an estimated price for the sale of the rank (A) condition by multiplying the selling price for the rank (A) condition by the same correction coefficient for all conditions.

For example, if there are condition ranks (S, A, B, C, D) and second-hand product information for some of these conditions is lacking, the determination device 100 calculates an estimated price for the sale of the part of the condition for which second-hand product information is lacking by multiplying the sales price of the standard condition output from the model based on the second-hand product information of the standard condition by a correction coefficient corresponding to the part of the condition for which second-hand product information is lacking. For example, if the standard condition is condition rank (B) and second-hand product information for condition rank (A) is lacking, the determination device 100 calculates an estimated price for the sale of condition rank (A) by multiplying the sales price of condition rank (B) by a correction coefficient corresponding to condition rank (A). This allows the determination device 100 to set an appropriate price even when second-hand product information is lacking for some conditions.

In addition, for example, if the estimated price for selling a certain condition becomes higher than the estimated price for selling a condition higher than the certain condition, causing a reversal, the determination device 100 calculates the estimated price for selling the certain condition where the reversal occurred by multiplying the selling price of the standard condition output from the model based on the used item information of the standard condition by a correction coefficient corresponding to the certain condition where the reversal occurred. For example, assume that there are condition ranks (S, A, B, C, D) and the standard condition is condition rank (B). Then, if the estimated price for selling a condition of rank (C) becomes higher than the estimated price for selling a condition of the higher rank (B), causing a reversal, the determination device 100 calculates the estimated price for selling a condition of rank (C) by multiplying the selling price of the condition of rank (B) by a correction coefficient corresponding to the condition of rank (C).

In addition, if the estimated price for selling a product in a condition of rank (A) becomes lower than the estimated price for selling a product in a condition of a lower rank (B), resulting in a reversal, the determination device 100 calculates the estimated price for selling a product in a condition of rank (A) by multiplying the selling price for a product in a condition of rank (B) by a correction coefficient corresponding to the condition of rank (A). This allows the determination device 100 to appropriately correct the price if an error occurs in the model learning and the estimated price is reversed.

The correction coefficient to be multiplied by the sales price is explained below. The longer the period (e.g., the number of days elapsed) between the start of sales of new products and the most recent purchase of a used product, the smaller the correction coefficient will be. Note that the shorter the period, the larger the correction coefficient may be. In this case, depending on sales history, the sooner a used product sells, the larger the correction coefficient will be, so the calculated estimated price will be higher and the used product may become a premium product. Also, the degree to which the correction coefficient decreases or increases depending on the period may differ depending on the condition.

Then, the determination device 100 determines the calculated estimated price as the estimated price for sale for each condition (step S107). In this way, the determination device 100 determines the estimated price for sale for each condition based on the new product information and the used product information. This allows the determination device 100 to estimate the price based on both the new product information and the used product information, making it possible to set an appropriate price with high accuracy. Furthermore, the determination device 100 can estimate the price for each condition, making it possible to set an appropriate price.

It is also assumed that an upper limit price may be set. Here, a coefficient to be multiplied by the selling price to obtain the upper limit price is set as a specific coefficient. The specific coefficient is, for example, predetermined for each product class (for example, a combination of brand and category). The determination device 100 may compare a corrected price obtained by multiplying the selling price by the correction coefficient with an upper limit price obtained by multiplying the selling price by the specific coefficient, and if the corrected price exceeds the upper limit price, the determination device 100 may set the upper limit price as an estimated price. This allows the determination device 100 to optimize price setting so that used products become premium products and do not deviate significantly from the list price of new products. In addition, the determination device 100 can set an upper limit price according to each product class by using a specific coefficient predetermined for each product class.

(Decision Process Variation 1)
In the above embodiment, the determination device 100 may determine a purchase price based on the estimated price for sale for each condition. The determination device 100 may provide the purchase price determined based on the estimated price for sale for the standard condition to the user U11 as a trade-in price by transmitting information for display on the user terminal 10 (step S108). The determination device 100 may also provide the purchase price determined based on the estimated price for sale for each condition to the seller of the secondhand goods for each condition by transmitting information for display on the seller's terminal for each condition.

(Decision Process Variation 2)
In the above embodiment, when listing an item in consideration of market demand, the pricing process according to the above embodiment may be performed during a period of high market demand. For example, seasonal items (seasonal items) may be determined in advance, and when the purchased second-hand item is a seasonal item, the item may be left to sit until a period of high market demand before being listed, thereby performing the pricing process according to the above embodiment during a period of high market demand. For example, when a summer item is purchased in winter, the item may be left to sit until summer before being listed, thereby performing the pricing process according to the above embodiment during a period of high market demand. When listing an item in consideration of market demand, the determination device 100 determines an estimated price for sale for each condition during a period of high market demand. This allows the determination device 100 to set a price in consideration of market demand.

(Decision Process Variation 3)
In the above embodiment, a case has been described in which the user U11 requests the purchase of used clothing P11, and the selling price, estimated price, and trade-in price for each condition of the used item are determined based on the information for requesting the purchase of the used clothing P11 sent from the user terminal 10, but this is not limited to the example. For example, the selling price, estimated price, and trade-in price for each condition of the used item may be determined for all (or some) items sold in a specific online shopping mall, and the trade-in price may be presented to the user U11. In this case, the user U11 may select an item after looking at the trade-in price, and request the purchase of the used clothing P11. Details of the process will be described below.

The determination device 100 acquires new product information and used product information for each product for all (or some) products sold in a specified online shopping mall. The determination device 100 also inputs the new product information and used product information into a model for each product, thereby determining the selling price, estimated price, and trade-in price for each condition of the used product for each product. The determination device 100 then determines whether or not there is a product sold in a specified online shopping mall among the possessions of the user U11, and if it determines that there is a product sold in a specified online shopping mall, transmits information for displaying the trade-in price of the product on the user terminal 10. For example, if there are multiple products sold in a specified online shopping mall among the possessions of the user U11, the determination device 100 transmits information for displaying the trade-in price for each of the multiple products on the user terminal 10. Note that the possessions of the user U11 are identified, for example, based on the purchase history of the user U11 in a specified online shopping mall. Furthermore, when the possessions of user U11 are identified based on the purchase history of user U11 in a specific online shopping mall, the determination device 100 transmits, for example, information to display the trade-in price of the product as information on the product purchased by user U11 in the specific online shopping mall on the purchase page of user U11 in the specific online shopping mall. Then, the user terminal 10 transmits information for requesting the purchase of the second-hand product by user U11 selecting the product from among the products with the trade-in price displayed. For example, when user U11 selects a product corresponding to used clothing P11, the user terminal 10 transmits information for requesting the purchase of used clothing P11.

1-3. User terminal configuration
Next, the configuration of the user terminal 10 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the user terminal 10 according to the embodiment. As shown in Fig. 3, the user terminal 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

(Communication unit 11)
The communication unit 11 is realized by, for example, a network interface card (NIC) etc. The communication unit 11 is connected to a predetermined network N by wire or wirelessly, and transmits and receives information to and from the determination device 100 etc. via the predetermined network N.

(Input unit 12)
The input unit 12 accepts various operations from a user. In Fig. 2, the input unit 12 accepts various operations from a user U11. For example, the input unit 12 may accept various operations from a user via a display surface using a touch panel function. The input unit 12 may also accept various operations from buttons provided on the user terminal 10 or a keyboard or mouse connected to the user terminal 10.

(Output unit 13)
The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays information transmitted from the determination device 100.

(Control unit 14)
The control unit 14 is, for example, a controller, and is realized by a CPU (Central Processing Unit), MPU (Micro Processing Unit), etc., executing various programs stored in a storage device inside the user terminal 10 using a RAM (Random Access Memory) as a working area. For example, the various programs include application programs installed in the user terminal 10. For example, the various programs include an application program that transmits information for requesting a purchase to the determination device 100. The control unit 14 is also realized by an integrated circuit, for example, an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing functions described below.

(Receiving unit 141)
The receiving unit 141 receives various information from an external information processing device. The receiving unit 141 receives various information from other information processing devices such as the determination device 100. For example, the receiving unit 141 receives information for displaying the trade-in price.

(Transmitter 142)
The transmission unit 142 transmits various information to an external information processing device. The transmission unit 142 transmits various information to another information processing device such as the determination device 100. For example, the transmission unit 142 transmits information for requesting a purchase accepted from a user.

1-4. Configuration of the Determination Device
Next, a configuration of the determination device 100 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the configuration of the determination device 100 according to the embodiment. As shown in Fig. 4, the determination device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. Note that the determination device 100 may include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator of the determination device 100, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the user terminal 10 etc. via the network N.

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 4 , the storage unit 120 has a new product information storage unit 121 and a used product information storage unit 122.

The new product information storage unit 121 stores predetermined new product information (e.g., information such as the list price of the new product, the time of release, brand, and category) linked to the model number. FIG. 5 shows an example of the new product information storage unit 121 according to the embodiment. As shown in FIG. 5, the new product information storage unit 121 has items such as "model number" and "new product information."

"Model number" indicates the model number used to identify the product in a specific online shopping mall. "New product information" indicates new product information.

In other words, Figure 5 shows an example in which new product information for a product identified by model number "YYXX11" is "List price: 5,000 yen, Release date: January 1, 2000, Brand: AABB, Category: T-shirt (white)."

The used item information storage unit 122 stores predefined used item information linked to model numbers (e.g., the selling price n times ago, the discount rate at the last sale, the increase or decrease in the selling price from the time before last, the number of days from the last listing to the sale, the purchase (trade-in) price, and information related to the purchase (trade-in) year). FIG. 6 shows an example of the used item information storage unit 122 according to the embodiment. As shown in FIG. 6, the used item information storage unit 122 has items such as "model number" and "used item information".

"Model number" indicates identification information for identifying a product in a specific online shopping mall. "Used product information" indicates used product information.

In other words, Figure 6 shows an example in which the second-hand product information for a product identified by model number "YYXX11" is "Last selling price: 3,000 yen; selling price before last: XXX yen; selling price three times before: XXX yen; selling price four times before: XXX yen, discount rate at last sale: 10%, change in selling price from the time before last: 5% increase, number of days from last listing to sale: 2 weeks, purchase price: 1,000 yen, purchase year: 2021."

(Control unit 130)
The control unit 130 is a controller, and is realized, for example, by a CPU, an MPU, or the like, executing various programs stored in a storage device inside the determination device 100 using a RAM as a working area. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC or an FPGA.

As shown in FIG. 4, the control unit 130 has an acquisition unit 131, an identification unit 132, a generation unit 133, a determination unit 134, a calculation unit 135, a decision unit 136, and a provision unit 137, and realizes or executes the information processing action described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be other configurations as long as they perform the information processing described below.

(Acquisition unit 131)
The acquisition unit 131 acquires various pieces of information. The acquisition unit 131 acquires various pieces of information from an external information processing device. The acquisition unit 131 acquires various pieces of information from another information processing device such as the user terminal 10.

The acquisition unit 131 acquires various information from the storage unit 120. The acquisition unit 131 acquires various information from the new product information storage unit 121 and the used product information storage unit 122. The acquisition unit 131 also stores the acquired various information in the storage unit 120. The acquisition unit 131 stores the various information in the new product information storage unit 121 and the used product information storage unit 122.

The acquisition unit 131 acquires, for example, information for requesting the purchase of a product transmitted from the user terminal 10. Then, based on the information for requesting the purchase of a product, the acquisition unit 131 acquires, for example, business information of a specified service for which the purchase of the product has been requested, and business information of a specified online shopping mall where the user purchased a new copy of the same product.

(Identification unit 132)
The identification unit 132 determines whether or not the predetermined service for which the purchase of the product has been requested has a predetermined relationship with a predetermined online shopping mall where the user has purchased a new product of the same product, for example, based on the information acquired by the acquisition unit 131. For example, the identification unit 132 determines whether or not they are the same business operator, and whether or not the business operator of one service belongs to the business operator of the other service. When the identification unit 132 determines that the predetermined service for which the purchase of the product has been requested has a predetermined relationship with a predetermined online shopping mall where the user has purchased a new product of the same product, it acquires a purchase history in the predetermined online shopping mall that has been determined to have the predetermined relationship, and identifies the model number of the new product of the same product in the predetermined online shopping mall that has been determined to have the predetermined relationship, based on the acquired purchase history.

In addition, if the identification unit 132 determines that the specified service for which the purchase of the product has been requested does not have a specified relationship with the specified online shopping mall where the user purchased a new product of the same product, it identifies the model number of a new product of the same product in a specified online shopping mall that has a specified relationship with the specified service for which the purchase of the product has been requested, for example, based on tag information attached to the actual product sent to a store of the specified service for which the purchase has been requested.

(Generation unit 133)
The generating unit 133 generates a model that outputs a selling price for each condition of a used item based on new product information and used product information of a product with a sales record. For example, the generating unit 133 generates a model based on XGBoost or the like by using new product information of a product with a sales record and used product information up to the last time of sale as explanatory variables and the last selling price as a target variable. In this way, the generating unit 133 generates a model that outputs the last selling price, for example, the selling price from the time before last to the fifth time before, by using the used product information up to the last time of sale as an explanatory variable. Note that the product with a sales record may be the same product as the product requested to be purchased, or may be a product different from the product requested to be purchased. In addition, the generating unit 133 trains the model using the selling price of a predetermined condition, which is predetermined as a reference condition, among the conditions of used items, as a positive example.

(Determination unit 134)
The determination unit 134 determines whether or not secondhand product information for some conditions is insufficient. When the determination unit 134 determines that secondhand product information for some conditions is insufficient, it specifies the part of the conditions for which secondhand product information is insufficient.

The determination unit 134 determines whether or not a reversal has occurred because the estimated price for the sale of some conditions is higher than the estimated price for the sale of a condition higher than the some conditions. If the determination unit 134 determines that a reversal has occurred because the estimated price for the sale of a condition higher than the some conditions is higher, the determination unit 134 identifies the some conditions for which the reversal has occurred.

(Calculation Unit 135)
The calculation unit 135 acquires new product information and used product information that are predetermined in association with the model number of the new product identified by the identification unit 132. That is, the calculation unit 135 acquires the new product information and used product information to be input to the model generated by the generation unit 133. The calculation unit 135 then inputs the acquired new product information and used product information to the model generated by the generation unit 133, thereby calculating the selling price for each condition of the used product. In this manner, the generation unit 133 generates a model that outputs the previous selling price, for example, from the selling prices from before last to the fifth selling price, and the calculation unit 135 calculates the future selling price, from the selling prices from the previous to the fourth selling price.

The calculation unit 135 calculates the estimated price for the sale for each condition by multiplying the calculated selling price for each condition by a correction coefficient. For example, the calculation unit 135 calculates the estimated price for the sale for each condition by multiplying the selling price for each condition by the same correction coefficient.

The calculation unit 135 multiplies the sales price of the standard condition output from the model based on the used item information of the standard condition by a correction coefficient corresponding to the part of the condition for which used item information is lacking, identified by the determination unit 134, to calculate an estimated price for the sale of the part of the condition for which used item information is lacking.

The calculation unit 135 multiplies the sales price of the standard condition output from the model based on the used item information of the standard condition by a correction coefficient corresponding to the partial condition of the item in which the inversion has occurred, as identified by the determination unit 134, to calculate an estimated price for the sale of the partial condition of the item in which the inversion has occurred.

(Determination Unit 136)
The determination unit 136 determines the estimated price calculated by the calculation unit 135 as the estimated price for the sale for each condition. The calculation unit 135 also compares, for example, a corrected price obtained by multiplying the selling price by a correction coefficient with an upper limit price obtained by multiplying the selling price by a specific coefficient, and determines whether the corrected price exceeds the upper limit price. If the calculation unit 135 determines that the corrected price exceeds the upper limit price, it sets the upper limit price as the estimated price.

(Providing Unit 137)
The providing unit 137 transmits information for displaying the purchase price determined based on the estimated price for the sale of the standard condition as the trade-in price on the user terminal 10. The providing unit 137 also transmits information for displaying the purchase price determined based on the estimated price for the sale of each condition on the seller's terminal device for each condition.

1-5. Decision process flow
Next, a procedure of the determination process by the determination system 1 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the procedure of the determination process by the determination system 1 according to the embodiment.

As shown in FIG. 7, the determination device 100 acquires new product information for the product that the user has requested to be purchased and used product information for used products that have sold the same product in the past (step S201).

The determination device 100 calculates the selling price for each condition of the used item based on the acquired new item information and used item information (step S202).

The determination device 100 determines an estimated price for the sale of the used item for each condition based on the calculated selling price for each condition (step S203).

2. Second embodiment
In pricing used goods, the purchased goods are priced, but in the case where the listing is suspended for a certain period between purchase and listing, if the price is set on the day of purchase and the price is set as the price at the time of listing, the price may become low. For example, if summer goods such as sleeveless dresses and swimsuits are purchased in winter, when there is little demand in the market, and the price is adopted as it is when listing six months later, the price may become low even though the goods are actually worth more and there are consumers who will buy them at a higher price, and the profit that should have been obtained may be lost. For this reason, in a pricing model in which the price is set on the day of purchase, since the price of used goods gradually decreases, it is difficult to predict the price of goods whose prices gradually increase, and there is a high possibility that the price will be set low. In the following embodiment 2, the price set on the day of purchase is appropriately referred to as "primary pricing" and the price set after a certain period has passed since the purchase is referred to as "secondary pricing". The same pricing process can be used for both primary and secondary pricing, and for example, the pricing process according to embodiment 1 can be used. In the second embodiment, the probability of an immediate sale is the probability of an immediate sale (for example, the probability of selling on the same day it is put up for sale).

In this application, a quick sale prediction is performed in parallel with the secondary pricing, and the listing price is determined by predicting whether the item will sell quickly and identifying items that are likely to be discounted. For example, for items that are likely to sell quickly after being listed, the listing price is adjusted to be higher.

2-1. Configuration of the decision system
The determination system 1A shown in Fig. 8 will be described. As shown in Fig. 8, the determination system 1A includes a business operator terminal 20 and a determination device 100A. The business operator terminal 20 and the determination device 100A are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other by wire or wirelessly. Fig. 8 is a diagram showing a configuration example of the determination system 1A according to the second embodiment.

The business operator terminal 20 is an information processing device used by a business operator who prices purchased products (i.e., a business operator who purchases used products). The business operator terminal 20 may be any device that can realize the processing in embodiment 2. The business operator terminal 20 may also be a device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. Figure 8 shows the case where the business operator terminal 20 is a smartphone.

The operator terminal 20 is, for example, a smart device such as a smartphone or tablet, and is a mobile terminal device that can communicate with any server device via a wireless communication network such as 3G to 5G or LTE. The operator terminal 20 also has a screen such as a liquid crystal display with touch panel functionality, and may accept various operations on displayed data such as content, such as tapping, sliding, scrolling, etc., performed by a finger or stylus from the operator. In FIG. 9, the operator terminal 20 is used by operator A11.

The determination device 100A is an information processing device intended to improve the accuracy of pricing used goods, and may be any device capable of implementing the processing in embodiment 2. The determination device 100A is realized, for example, by a server device or a cloud system. For example, the determination device 100A is realized by a server device or a cloud system of a business that prices used goods and puts them up for sale.

2-2. An example of the decision process
In the second embodiment below, a selling price (the price at which an item is likely to sell) is estimated based on past selling prices (the prices at which the item was actually sold), and a listing price (the estimated price in the first embodiment) is determined based on the selling price (the price at which the item is likely to sell). In addition, a probability of an immediate sale when the item is listed at the listing price determined in the secondary pricing is estimated, and the listing price is determined (or changed) based on the probability of an immediate sale. In the following, the estimated price in the first embodiment will be appropriately referred to as the "target listing price" to distinguish it from the listing price in the second embodiment.

9 is a diagram showing an example of the determination process of the determination system 1A according to the second embodiment. The determination device 100A generates an instant sale probability estimation model that estimates the current instant sale probability of a product purchased in the past (step S301). Specifically, the determination device 100A generates an instant sale probability estimation model that estimates whether or not the product will sell immediately as an objective variable. The instant sale probability estimation model is a model that outputs whether or not the product will sell immediately (for example, a value between "1" (if it will sell) or "0" (if it will not sell) or between "1" (if it will sell) and "0" (if it will not sell)) when information such as the condition of the product and the target listing price are input. For example, the instant sale probability estimation model is a model that learns whether or not the product will sell immediately as output information, using information such as the condition of the product and the target listing price as input information. For example, the instant sale probability estimation model is a model that learns whether or not the product will sell immediately from past sales records and various explanatory variables on a single product x condition basis. Therefore, by using the instant sale probability estimation model, it is possible to predict whether or not an unlisted product will sell immediately. The various explanatory variables of the quick sale probability estimation model include, for example, the listing date, the unit of prediction for the condition of a single item, the gender targeted by the product, the condition, sales, new price, the discount rate from the previous sale, the purchase time, the initial bid price, the number of days until the previous sale, whether the number of days until the sale has been shortened since the previous sale, and brand groups categorized by sales price range. Also, an importance may be set for each of the various explanatory variables of the quick sale probability estimation model.

The determination device 100A acquires the current target listing price (or sales price) of a product purchased in the past (step S302). For example, the determination device 100A acquires the current target listing price (or sales price) of a product purchased and initially priced six months ago. In the following embodiment 2, product A is used as an example of a product purchased in the past. The determination device 100A then estimates the current probability of an immediate sale of product A by inputting information such as the target listing price and condition of product A into an immediate sale probability estimation model (step S303). Depending on this probability of immediate sale, it becomes possible to predict whether product A will be sold immediately. For example, the determination device 100A may determine whether product A will be sold immediately depending on whether the probability of immediate sale of product A exceeds a predetermined threshold.

The determination device 100A determines the listing price of the product A according to the current probability of immediate sale of the product A (step S304). For example, when the probability of immediate sale exceeds a predetermined threshold, the determination device 100A predicts immediate sale and therefore determines to set the listing price of the product A at a high price in order to increase profits. Also, for example, when the probability of immediate sale falls below a predetermined threshold, the determination device 100A determines the current target listing price of the product A as the listing price of the product A. Note that when the probability of immediate sale falls below a predetermined threshold, the determination device 100A may determine to set the listing price of the product A at a low price since the product A is more likely to remain unsold. The determination device 100A may determine the listing price of the product A based on tertiary pricing, which sets the price lower than the listing price of secondary pricing. The determination device 100A then transmits information on the determined listing price of the product A to the business terminal 20 (step S305).

[2-3. Processing variations]
(Determining the listing price using a table)
In the above-mentioned second embodiment, the determination device 100A may determine the selling price based on a table that associates the probability of immediate sale with information for determining the selling price. For example, the table includes information such as setting the selling price to 1.2 times the current target selling price when the probability of immediate sale is 70 to 80%, setting the selling price to 1.3 times the current target selling price when the probability of immediate sale is 80 to 90%, and setting the selling price to 1.5 times the current target selling price when the probability of immediate sale is 90 to 100%. Based on such a table, the determination device 100A may determine, for example, to set the selling price to 1.2 times the current target selling price when the probability of immediate sale of the product A is 75%, to set the selling price to 1.3 times the current target selling price when the probability of immediate sale of the product A is 85%, and to set the selling price to 1.5 times the current target selling price when the probability of immediate sale of the product A is 95%.

(Current selling price estimate based on price estimation model)
In the above-mentioned second embodiment, the determination device 100A may estimate the current selling price based on a price estimation model that has learned the characteristics of the past selling price, and may determine the listing price using the estimated current selling price. The determination device 100A may generate a price estimation model that estimates the selling price as a target variable. The price estimation model is, for example, a model that outputs a selling price when information such as the condition of a product is input. For example, the price estimation model is a model that is trained with information such as the condition of a product as input information and the selling price at the time of actual sale as output information. The determination device 100A may estimate the current selling price of the product A based on the price estimation model that has learned the characteristics of the past selling price of the product A. The determination device 100A may estimate the current immediate selling probability of the product A by inputting the target listing price based on the selling price of the product A determined by the secondary pricing into the immediate selling probability estimation model.

(Use of the highest auction price within a given period)
In the above-mentioned second embodiment, the determination device 100A may determine the listing price from among the listing prices according to the probability of immediate sale estimated within a predetermined period. For example, the determination device 100A calculates a plurality of listing prices by estimating the probability of immediate sale at a predetermined frequency within a predetermined period. Then, the determination device 100A may identify the highest listing price among the plurality of listing prices and determine the listing price as the listing price. For example, when the product A is to be listed tomorrow, the determination device 100A may determine the listing price of the product A by identifying the highest listing price among the listing prices of the product A in the past week. For example, when the product A is to be listed on November 29, 2022, the determination device 100A may determine the listing price of the product A as of November 29, 2022 from among the listing prices according to the probability of immediate sale estimated during the period from November 21, 2022 to November 28, 2022. For example, if the listing price of the product A on November 22, 2022 is 2000 yen and the listing price of the product A on November 23, 2022 is 3000 yen, the determination device 100A may determine the higher listing price of 3000 yen as a candidate for the listing price and determine the listing price of the product A based on the comparison result with the listing price of the product A at other times. In addition, the determination device 100A may specify the highest listing price and determine it as the listing price, but this is not limited to the example. For example, the determination device 100A may calculate the average of multiple listing prices and determine it as the listing price. For example, when the product A is to be listed tomorrow, the determination device 100A may determine the listing price of the product A by calculating the average of the listing price of the product A for the past week. In addition, when the product A is to be listed in a place where fluctuations are expected from time to time, such as an auction, the determination device 100A may determine the listing price each time the immediate sale probability is estimated at a predetermined frequency. For example, when product A is put up for auction, the determination device 100A may estimate the probability of product A being sold immediately for each day and determine the selling price of product A for each day.

(Repeat until the probability of immediate sale falls below a certain threshold.)
In the above-mentioned second embodiment, the determination device 100A may re-estimate the current probability of selling immediately by inputting the target selling price into the instant selling probability estimation model. Then, the determination device 100A may re-determine the listing price according to the estimated instant selling probability. At this time, the determination device 100A may determine whether the estimated selling probability exceeds a predetermined threshold, and if the instant selling probability exceeds the predetermined threshold, may input the listing price according to the instant selling probability into the instant selling probability estimation model as the current listing price, thereby re-estimating the current probability of selling immediately. Also, the determination device 100A may determine whether the estimated instant selling probability exceeds a predetermined threshold, and if the instant selling probability falls below the predetermined threshold, may determine the listing price according to the instant selling probability, or may determine the listing price according to the instant selling probability estimated immediately before. Then, the determination device 100A may determine the listing price by repeating the above process until the instant selling probability falls below the predetermined threshold. To give a specific example, when the current target listing price (or the listing price) is 1000 yen, the current probability of immediate sale at the target listing price (or the listing price) is 95%, and the predetermined threshold is 70%, the determination device 100A estimates the probability of immediate sale as a new current target listing price (or the listing price) that is 1500 yen, which is 1.5 times 1000 yen, since the current probability of immediate sale exceeds the predetermined threshold. Then, when the probability of immediate sale at 1500 yen is 75%, the determination device 100A estimates the probability of immediate sale as a new current target listing price (or the listing price) that is 1800 yen, which is 1.2 times 1500 yen, since the current probability of immediate sale still exceeds the predetermined threshold. Then, when the probability of immediate sale at 1800 yen is 60%, the determination device 100A determines the listing price to be 1800 yen or 1500 yen according to the probability of immediate sale estimated immediately before, since the current probability of immediate sale is below the predetermined threshold.

2-4. Configuration of carrier terminal
Next, the configuration of the operator terminal 20 according to the second embodiment will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of the configuration of the operator terminal 20 according to the second embodiment. As shown in Fig. 10, the operator terminal 20 has a communication unit 21, an input unit 22, an output unit 23, and a control unit 24.

(Communication unit 21)
The communication unit 21 is realized by, for example, a NIC etc. The communication unit 21 is connected to a predetermined network N by wired or wireless connection, and transmits and receives information to and from the determination device 100A etc. via the predetermined network N.

(Input unit 22)
The input unit 22 accepts various operations from the business operator. In Fig. 9, the input unit 22 accepts various operations from the business operator A11. For example, the input unit 22 may accept various operations from the business operator via a display screen using a touch panel function. The input unit 22 may also accept various operations from buttons provided on the business operator terminal 20 or a keyboard or mouse connected to the business operator terminal 20.

(Output unit 23)
The output unit 23 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display, an organic EL display, etc., and is a display device for displaying various information. For example, the output unit 23 displays information transmitted from the determination device 100A.

(Control unit 24)
The control unit 24 is, for example, a controller, and is realized by a CPU, an MPU, or the like executing various programs stored in a storage device inside the business terminal 20 using a RAM as a working area. For example, these various programs include application programs installed in the business terminal 20. For example, these various programs include application programs that accept products for which auction prices are to be determined. The control unit 24 is also realized by an integrated circuit, for example, an ASIC, an FPGA, or the like.

As shown in FIG. 10, the control unit 24 has a receiving unit 241 and a transmitting unit 242, and realizes or executes the information processing functions described below.

(Receiving unit 241)
The receiving unit 241 receives various information from an external information processing device. The receiving unit 241 receives various information from other information processing devices such as the determination device 100A. For example, the receiving unit 241 receives information for displaying the auction price of a product designated by a business operator.

(Transmitter 242)
The transmission unit 242 transmits various information to an external information processing device. The transmission unit 242 transmits various information to other information processing devices such as the determination device 100A. For example, the transmission unit 242 transmits information on a product designated by a business operator in order to determine the auction price.

2-5. Configuration of the Determination Device
Next, the configuration of the determination device 100A according to the second embodiment will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of the configuration of the determination device 100A according to the second embodiment. As shown in Fig. 11, the determination device 100A includes a communication unit 110A, a storage unit 120A, and a control unit 130A. Note that the determination device 100A may include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator of the determination device 100A, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

(Communication unit 110A)
The communication unit 110A is realized by, for example, a NIC etc. The communication unit 110A is connected to the network N by wire or wirelessly, and transmits and receives information to and from the carrier terminal 20 etc. via the network N.

(Memory unit 120A)
The storage unit 120A is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in Fig. 11, the storage unit 120A has a selling price storage unit 121A and an immediate sales result storage unit 122A.

The sales price memory unit 121A stores the past sales prices of products. FIG. 12 shows an example of the sales price memory unit 121A according to the second embodiment. As shown in FIG. 12, the sales price memory unit 121A has items such as "product ID," "sales period," "sales price," and "condition."

"Product ID" indicates identification information for identifying a product. "Sales date" indicates the past sales date when the product was sold. "Sales price" indicates the past sales price. "Condition" indicates the condition of the product when it was sold.

The immediate sales result storage unit 122A stores the listing price of the product and the immediate sales result in association with each other. FIG. 13 shows an example of the immediate sales result storage unit 122A according to the second embodiment. As shown in FIG. 13, the immediate sales result storage unit 122A has items such as "product ID," "listing time," "listing price," "condition," and "immediate sales result."

"Product ID" indicates identification information for identifying a product. "Listing date" indicates the previous listing date of the product. "Listing price" indicates the previous listing price. "Condition" indicates the condition of the product when it was listed. "Instant sales result" indicates whether the product was sold immediately or not.

(Control unit 130A)
The control unit 130A is a controller, and is realized, for example, by a CPU, an MPU, or the like, executing various programs stored in a storage device inside the determination device 100A using a RAM as a working area. The control unit 130A is also realized, for example, by an integrated circuit such as an ASIC or an FPGA.

As shown in FIG. 11, the control unit 130A has an acquisition unit 131A, a generation unit 132A, an estimation unit 133A, a determination unit 134A, and a provision unit 135A, and realizes or executes the information processing action described below. Note that the internal configuration of the control unit 130A is not limited to the configuration shown in FIG. 11, and may be other configurations as long as they perform the information processing described below.

(Acquisition unit 131A)
The acquisition unit 131A acquires various information. The acquisition unit 131A acquires various information from an external information processing device. The acquisition unit 131A acquires various information from other information processing devices such as the business terminal 20. The acquisition unit 131A also acquires various information from the memory unit 120A. The acquisition unit 131A acquires various information from the selling price memory unit 121A and the immediate sales result memory unit 122A. The acquisition unit 131A also stores the acquired various information in the memory unit 120A. The acquisition unit 131A stores the various information in the selling price memory unit 121A and the immediate sales result memory unit 122A.

The acquisition unit 131A, for example, acquires the current selling price information and target listing price information of the target product. The acquisition unit 131A also acquires, for example, past selling price information and listing price information of the target product. The acquisition unit 131A also acquires, for example, instant sales results corresponding to the past listing prices of the target product. The acquisition unit 131A also acquires, for example, a price estimation model. The acquisition unit 131A also acquires, for example, an instant sales probability estimation model.

(Generation unit 132A)
The generating unit 132A generates a price estimation model. For example, the generating unit 132A generates a price estimation model that has been trained on the characteristics of the past selling price of the target product. For example, the generating unit 132A generates a price estimation model that has been trained on information such as the condition of the product as input information and the selling price at the time of actual sale as output information.

The generating unit 132A generates an instantaneous selling probability estimation model. For example, the generating unit 132A generates a model that learns whether an item will sell immediately from information such as the condition of the item and the target listing price as input information and whether an item will sell immediately from output information. For example, the generating unit 132A generates an instantaneous selling probability estimation model that learns whether an item will sell immediately from past sales records and various explanatory variables for each item and condition. For example, the generating unit 132A generates an instantaneous selling probability estimation model that learns whether an item will sell immediately from various explanatory variables such as the listing date, the prediction unit for the condition of the item, the gender of the item, the condition, sales, the new price, the discount rate at the time of the previous sale, the purchase time, the first pricing price, the second pricing price, the number of days until the item was sold in the past, whether the number of days until the item was sold has increased since the previous time, and the group of brands classified by the sales price range. For example, the generating unit 132A generates an instantaneous selling probability estimation model that learns whether an item will sell immediately by setting the importance of each of the various explanatory variables.

(Estimation unit 133A)
The estimation unit 133A estimates the current selling price of the target product. For example, the estimation unit 133A estimates the current selling price of the target product using a price estimation model. The estimation unit 133A also estimates the current probability of the target product being sold immediately. For example, the estimation unit 133A estimates the current probability of the target product being sold immediately using an instant selling probability estimation model. For example, the estimation unit 133A estimates the current probability of the target product being sold immediately by inputting a target listing price based on the selling price of the target product. The estimation unit 133A also estimates whether the target product is currently being sold immediately. For example, the estimation unit 133A estimates whether the target product is currently being sold immediately by inputting a target listing price of the target product.

(Determination unit 134A)
The determination unit 134A determines the current listing price of the target item according to the probability of quick selling estimated by the estimation unit 133A. For example, the determination unit 134A determines the listing price based on the probability of quick selling estimated by the estimation unit 133A and a table that associates the probability of quick selling with information for determining the listing price. For example, when the probability of quick selling is 75%, the determination unit 134A determines the listing price by multiplying the target listing price by 1.2.

(Providing unit 135A)
The providing unit 135A provides information for displaying the listing price determined by the determining unit 134A. Upon receiving the information transmitted from the providing unit 135A, the business operator terminal 20 displays the listing price appropriate for the market demand (i.e., the listing price that will result in a high profit or profit rate).

2-6. Decision process flow
Next, a procedure of the determination process by the determination system 1A according to the second embodiment will be described with reference to Fig. 14. Fig. 14 is a flowchart showing the procedure of the determination process by the determination system 1A according to the second embodiment.

As shown in FIG. 14, the determination device 100A obtains the target listing price of the target product (step S401).

The determination device 100A estimates the current probability of an immediate sale of the target product by inputting the acquired target listing price of the target product into an immediate sale probability estimation model that estimates the probability of an immediate sale of the target product (step S402).

The determination device 100A determines the listing price of the target product based on the estimated probability of immediate sale (step S403).

3. Effects
As described above, the determination device 100A according to the embodiment includes the estimation unit 133A and the determination unit 134A. The estimation unit 133A estimates the current probability of an immediate sale of the target item based on the current target listing price of the target item and an immediate sale probability estimation model that estimates the immediate sale probability of the target item. The determination unit 134A determines the listing price of the target item according to the immediate sale probability estimated by the estimation unit 133A.

As a result, the determination device 100A according to the embodiment can improve the accuracy of pricing used items. It can also determine the listing price so that the item is not underpriced.

In addition, the estimation unit 133A estimates the current selling price of the target product based on a price estimation model that is a selling price for determining the target listing price and that has learned the characteristics of the past selling prices of the target product.

This allows the determination device 100A according to the embodiment to appropriately estimate the sales price based on past sales performance.

In addition, the estimation unit 133A estimates the current probability of an immediate sale of the target product based on an immediate sale probability estimation model trained using the purchase time as an explanatory variable.

This allows the determination device 100A according to the embodiment to improve the accuracy of estimating the probability of immediate sale.

In addition, the determination unit 134A sets the listing price to a high price if the probability of immediate sale exceeds a predetermined threshold.

This allows the determination device 100A according to the embodiment to determine the listing price so that it is not too cheap.

In addition, the determination unit 134A determines the listing price based on information that associates the probability of quick sale with information for determining the listing price.

This allows the determination device 100A according to the embodiment to appropriately adjust the listing price. For example, the price adjustment can be appropriately performed based on a table.

The determination unit 134A also determines the listing price by repeating the estimation of the probability of an immediate sale and the determination of the listing price, assuming the listing price to be the current target listing price of the target product, until the probability of an immediate sale falls below a predetermined threshold.

This allows the determination device 100A according to the embodiment to adjust the listing price so that it is not underpriced.

In addition, the determination unit 134A determines the highest listing price among the listing prices estimated within a specified period according to the probability of quick sale as the listing price.

As a result, the determination device 100A according to the embodiment can determine the listing price so as to maximize profits and profit margins. For example, the highest price in the past week can be determined as the listing price.

4. Hardware Configuration
The operator terminal 20 and the determination device 100A according to the second embodiment described above are realized, for example, by a computer 1000 having a configuration as shown in Fig. 15. Fig. 15 is a hardware configuration diagram showing an example of a computer that realizes the functions of the operator terminal 20 and the determination device 100A. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each component. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, and programs that depend on the hardware of the computer 1000, etc.

HDD 1400 stores programs executed by CPU 1100 and data used by such programs. Communication interface 1500 acquires data from other devices via a specified communication network and sends it to CPU 1100, and transmits data generated by CPU 1100 to other devices via the specified communication network.

The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input/output interface 1600. The CPU 1100 acquires data from the input devices via the input/output interface 1600. The CPU 1100 also outputs the data it generates to the output devices via the input/output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

For example, when the computer 1000 functions as the operator terminal 20 and the determination device 100A according to the second embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control units 24 and 130A by executing programs loaded onto the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 of the computer 1000 may obtain these programs from another device via a specified communication network.

[5. Other]
In addition, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

The above-mentioned embodiments can be combined as appropriate to the extent that they do not cause any contradictions in the processing content.

Although several embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the disclosure section of the invention.

The above-mentioned "section, module, unit" can be read as "means" or "circuit." For example, an acquisition unit can be read as an acquisition means or an acquisition circuit.

1, 1A Determination system 10 User terminal 11 Communication unit 12 Input unit 13 Output unit 14 Control unit 20 Business operator terminal 21 Communication unit 22 Input unit 23 Output unit 24 Control unit 100, 100A Determination device 110, 110A Communication unit 120, 120A Storage unit 121 New product information storage unit 121A Selling price storage unit 122 Used product information storage unit 122A Instant sales result storage unit 130, 130A Control unit 131, 131A Acquisition unit 132 Identification unit 132A Generation unit 133 Generation unit 133A Estimation unit 134 Judgment unit 134A Determination unit 135 Calculation unit 135A Provision unit 136 Determination unit 137 Provision unit 141 Reception unit 142 Transmission unit 241 Receiving unit 242 Transmitting unit N Network

Claims (8)

an estimation unit that estimates a current probability of immediate sale of the target product based on a current target listing price of the target product estimated based on a price estimation model that has learned characteristics of the past selling prices of the target product and an immediate sale probability estimation model that estimates the immediate sale probability of the target product;
a determination unit that determines a listing price of the target product in accordance with the quick sale probability estimated by the estimation unit;
having
The determination unit is
When the instantaneous selling probability does not fall below a predetermined threshold, the instantaneous selling probability is re-estimated as the target listing price for the instantaneous selling probability estimation model, and when the instantaneous selling probability falls below a predetermined threshold, the listing price is determined according to the instantaneous selling probability that has fallen below the predetermined threshold.
A determination device comprising: The estimation unit is
The probability of immediate sale is estimated based on the price estimation model that has learned the listing price determined according to the probability of immediate sale as a past selling price of the target product when the target product is sold at the listing price determined according to the probability of immediate sale.
2. The device according to claim 1 . The estimation unit is
The determination device according to claim 1 , further comprising: a determining unit that determines a current probability of the target product being sold immediately based on the probability of the target product being sold immediately, the probability of the target product being sold immediately being estimated ... being estimated The determination unit is
The device according to claim 1 , wherein the auction price is set to a high price when the probability of quick sale exceeds a predetermined threshold. The determination unit is
2. The device according to claim 1, further comprising: a device for determining the selling price that determines the selling price based on information that associates the probability of quick sale with information for determining the selling price. The determination unit is
2. The device according to claim 1, further comprising a step of determining the highest listing price among the listing prices according to the probability of quick sale estimated within a predetermined period as the listing price. 1. A computer implemented method for determining a
an estimation step of estimating a current probability of immediate sale of the target product based on a current target listing price of the target product estimated based on a price estimation model that has learned characteristics of the past selling prices of the target product and an immediate sale probability estimation model that estimates the immediate sale probability of the target product;
a determination step of determining a listing price of the target product in accordance with the probability of immediate sale estimated in the estimation step;
Including,
The determining step includes:
When the instantaneous selling probability does not fall below a predetermined threshold, the instantaneous selling probability is re-estimated as the target listing price for the instantaneous selling probability estimation model, and when the instantaneous selling probability falls below a predetermined threshold, the listing price is determined according to the instantaneous selling probability that has fallen below the predetermined threshold.
A method for determining whether or not a an estimation step of estimating a current probability of immediate sale of the target product based on a current target listing price of the target product estimated based on a price estimation model that has learned characteristics of the past selling prices of the target product and an immediate sale probability estimation model that estimates the immediate sale probability of the target product;
a determination step of determining a listing price of the target product in accordance with the quick sale probability estimated by the estimation step;
Run the following on your computer :
The determination procedure includes:
When the instantaneous selling probability does not fall below a predetermined threshold, the instantaneous selling probability is re-estimated as the target listing price for the instantaneous selling probability estimation model, and when the instantaneous selling probability falls below a predetermined threshold, the listing price is determined according to the instantaneous selling probability that has fallen below the predetermined threshold.
A decision program comprising:

Images