[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
Journals
JRFM
Special Issues
Machine Learning Based Risk Management in Finance and Insurance
share announcement

Machine Learning Based Risk Management in Finance and Insurance

A special issue of Journal of Risk and Financial Management (ISSN 1911-8074). This special issue belongs to the section "Financial Technology and Innovation".

Deadline for manuscript submissions: 31 October 2025 | Viewed by 4552

Special Issue Editors

Dr. Mohamed Chaouch

E-Mail Website
Guest Editor
Department of Mathematics, Statistics and Physics, Qatar University, Doha 2713, Qatar
Interests: financial econometrics; statistical learning for big data; copula-based modeling; functional data analysis
Prof. Dr. Thanasis Stengos

E-Mail Website
Guest Editor
Department of Economics and Finance, University of Guelph, Guelph, ON N1G2W1, Canada
Interests: nonparametric econometrics; applied time series models; empirical finance; empirical growth
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The finance and insurance industries are increasingly facing a rapidly changing landscape characterized by increased uncertainty, complex interdependencies, and the proliferation of high-dimensional and big data. Traditional risk management methods, while basic, are often challenged by these complexities, necessitating the integration of more sophisticated statistical and machine learning techniques. This Special Issue aims to cover the cutting edge of research and innovation in applying these advanced methodologies to quantitative risk management in finance and insurance.

We invite submissions that address a wide range of topics, including, but not limited to, portfolio optimization, credit risk modeling, insurance pricing, catastrophe modeling, systemic risk analysis, fraud detection, and algorithmic trading. Contributions to developing new models, improving existing techniques, or innovative applications of machine learning algorithms (e.g., deep learning, ensemble methods, and reinforcement learning) are strongly encouraged. In addition, we welcome research that addresses the challenges of model interpretation, robustness, and scalability and research that examines the ethical implications and regulatory aspects of implementing these techniques in real-world scenarios. This Special Issue also highlights interdisciplinary approaches that bridge the gap between finance, insurance, statistics, and computer science, providing new perspectives on managing and mitigating risk in an increasingly complex environment. Particular attention will be given to submissions that provide empirical evidence through case studies or propose methods/algorithms that combine machine learning with traditional risk management practices. By bringing together cutting-edge research and practical insights, this Special Issue aims to advance the field and serve as a critical resource for academics, industry professionals, and policymakers striving to improve risk management strategies in an era of unprecedented change.

Dr. Mohamed Chaouch
Prof. Dr. Thanasis Stengos
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Risk and Financial Management is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • quantitative risk management
  • financial risk
  • insurance risk
  • machine learning
  • statistical modeling
  • portfolio optimization
  • credit risk modeling
  • insurance pricing
  • catastrophe modeling
  • systemic risk
  • predictive analytics
  • deep learning
  • ensemble methods
  • reinforcement learning
  • fraud detection
  • algorithmic trading
  • model interpretability
  • regulatory compliance
  • high-dimensional data
  • model robustness
  • risk mitigation
  • ethical AI in finance

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Other

24 pages, 475 KiB  
Article
Price Gaps and Volatility: Do Weekend Gaps Tend to Close?
by Marnus Janse van Rensburg and Terence Van Zyl
J. Risk Financial Manag. 2025, 18(3), 132; https://doi.org/10.3390/jrfm18030132 - 3 Mar 2025
Viewed by 155
Abstract
This study investigates weekend price gaps in three major stock market indices—the Dow Jones Industrial Average (DJIA), NASDAQ, and Germany’s DAX—from 2013 to 2023, using high-frequency (5 min) data to explore whether gap movements arise from random volatility or reflect systematic market tendencies. [...] Read more.
This study investigates weekend price gaps in three major stock market indices—the Dow Jones Industrial Average (DJIA), NASDAQ, and Germany’s DAX—from 2013 to 2023, using high-frequency (5 min) data to explore whether gap movements arise from random volatility or reflect systematic market tendencies. We examine 205 weekend gaps in the DJIA, 270 in NASDAQ, and 406 in the DAX. Two principal hypotheses guide our inquiry as follows: (i) whether price movements into the gap are primarily driven by increased volatility and (ii) whether larger gaps are associated with heightened volatility. Employing Chi-square tests for the independence and linear regression analyses, our results show no strong, universal bias towards closing gaps at shorter distances across all three indices. However, at medium-to-large distances, significant directional patterns emerge, particularly in the DAX. This outcome challenges the assumption that weekend gaps necessarily “fill” soon after they open. Moreover, larger gap sizes correlate with elevated volatility in both the DJIA and NASDAQ, underscoring that gaps can serve as leading indicators of near-term price fluctuations. These findings suggest that gap-based anomalies vary by market structure and geography, raising critical questions about the universality of efficient market principles and offering practical insights for risk management and gap-oriented trading strategies. Full article
(This article belongs to the Special Issue Machine Learning Based Risk Management in Finance and Insurance)
►▼ Show Figures

Figure 1

Figure 1
<p>Hit rate comparison up to 990 points for DJIA (US30) showing flattening trends.</p> Full article ">Figure 2
<p>Hit rate comparison up to 990 points for NASDAQ (US100) showing flattening trends.</p> Full article ">Figure 3
<p>Hit rate comparison up to 990 points for Dax showing flattening trends.</p> Full article ">Figure 4
<p>Focused view hit rate comparison for DJIA (US30).</p> Full article ">Figure 5
<p>Focused view hit rate comparison for Dax.</p> Full article ">Figure 6
<p>Focused view hit rate comparison for NASDAQ (US100).</p> Full article ">
17 pages, 876 KiB  
Article
Machine Learning as a Tool for Assessment and Management of Fraud Risk in Banking Transactions
by Antonio Dichev, Silvia Zarkova and Petko Angelov
J. Risk Financial Manag. 2025, 18(3), 130; https://doi.org/10.3390/jrfm18030130 - 2 Mar 2025
Viewed by 256
Abstract
The present work aims to fill the gaps in existing research on the application of machine learning in fraud detection and management in the banking sector. It provides a theoretical perspective on the evolution of algorithms, highlights practical aspects, and derives relevant metrics [...] Read more.
The present work aims to fill the gaps in existing research on the application of machine learning in fraud detection and management in the banking sector. It provides a theoretical perspective on the evolution of algorithms, highlights practical aspects, and derives relevant metrics for evaluating their performance on unbalanced data. In the growing context of artificial intelligence, the adoption of an innovative, systematic approach to studying fraud in banking transactions through advanced machine learning algorithms is completely positive for the overall accuracy and effectiveness of risk management and has really practical and applied significance. The proven methodology (Classification and Regression Trees, Gradient Boosting, and Extreme Gradient Boosting) was tested on nearly 1.5 million in the banking sector, confirming the observations related to the application of fundamental assessments and specialized statistical methods through machine learning algorithms, demonstrating superior discriminatory power compared to classical models. The development provides valuable insights for managers, researchers, and policymakers aiming to strengthen the security and resilience of banking systems in times of evolving financial fraud challenges. Full article
(This article belongs to the Special Issue Machine Learning Based Risk Management in Finance and Insurance)
►▼ Show Figures

Figure 1

Figure 1
<p>Advantages vs. challenges and risks of machine learning. Source: Developed by the authors.</p> Full article ">Figure 2
<p>Comparative graph of the discriminatory power between all applied algorithms (validation sample). Source: Authors’ calculations.</p> Full article ">
22 pages, 4157 KiB  
Article
Prediction of Green Sukuk Investment Interest Drivers in Nigeria Using Machine Learning Models
by Mukail Akinde, Olasunkanmi Olapeju, Olusegun Olaiju, Timothy Ogunseye, Adebayo Emmanuel, Sekinat Olagoke-Salami, Foluke Oduwole, Ibironke Olapeju, Doyinsola Ibikunle and Kehinde Aladelusi
J. Risk Financial Manag. 2025, 18(2), 89; https://doi.org/10.3390/jrfm18020089 - 6 Feb 2025
Viewed by 615
Abstract
This study developed and evaluated machine learning models (MLMs) for predicting the drivers of green sukuk investment interest (GSII) in Nigeria, adopting the planks of hypothesised determinants adapted from variants of the planned behavioural model and behavioural finance theory. Of the seven models [...] Read more.
This study developed and evaluated machine learning models (MLMs) for predicting the drivers of green sukuk investment interest (GSII) in Nigeria, adopting the planks of hypothesised determinants adapted from variants of the planned behavioural model and behavioural finance theory. Of the seven models leveraged in the prediction, random forest, which had the highest level of accuracy (82.35% for testing and 90.37% for training datasets), with a good R2 value (0.774), afforded the optimal choice for prediction. The random forest model ultimately classified 10 of the hypothesised predictors of GSII, which underpinned constructs such as risk, perceived behavioural control, information availability, and growth, as highly important; 21, which were inclusive of all of the hypothesised constructs in measurement, as moderately important; and the remaining 15 as low in importance. The feature importance determined by the random forest model afforded an indicator-specific value, which can help green sukuk (GS) issuers to prioritise the most important drivers of investment interest, suggest important contexts for ethical investment policy enhancement, and inform insights about optimal resource allocation and pragmatic recommendations for stakeholders with respect to the funding of climate change mitigation projects in Nigeria. Full article
(This article belongs to the Special Issue Machine Learning Based Risk Management in Finance and Insurance)
►▼ Show Figures

Figure 1

Figure 1
<p>Flow chart of the methodology. Source: the authors’ constructs (2025).</p> Full article ">Figure 2
<p>Model accuracy comparison. Source: the authors’ constructs (2025).</p> Full article ">Figure 3
<p>Confusion matrix for random forest model. Source: the authors’ constructs (2025).</p> Full article ">Figure 4
<p>Confusion matrix for gradient boosting model. Source: the authors’ constructs (2025).</p> Full article ">Figure 5
<p>Confusion matrix for XGBoost model. Source: the authors’ constructs (2025).</p> Full article ">Figure 6
<p>Confusion matrix for SVM model. Source: the authors’ constructs (2025).</p> Full article ">Figure 7
<p>Confusion matrix for neural network model. Source: the authors’ constructs (2025).</p> Full article ">Figure 8
<p>Confusion matrix for logistic regression model. Source: the authors’ constructs (2025).</p> Full article ">Figure 9
<p>Confusion matrix for KNN model. Source: the authors’ constructs (2025).</p> Full article ">Figure 10
<p>Correlation heatmap for selected features. Source: the authors’ constructs (2025).</p> Full article ">
20 pages, 470 KiB  
Article
Modeling and Forecasting the Probability of Crypto-Exchange Closures: A Forecast Combination Approach
by Said Magomedov and Dean Fantazzini
J. Risk Financial Manag. 2025, 18(2), 48; https://doi.org/10.3390/jrfm18020048 - 22 Jan 2025
Viewed by 612
Abstract
The popularity of cryptocurrency exchanges has surged in recent years, accompanied by the proliferation of new digital platforms and tokens. However, the issue of credit risk and the reliability of crypto exchanges remain critical, highlighting the need for indicators to assess the safety [...] Read more.
The popularity of cryptocurrency exchanges has surged in recent years, accompanied by the proliferation of new digital platforms and tokens. However, the issue of credit risk and the reliability of crypto exchanges remain critical, highlighting the need for indicators to assess the safety of investing through these platforms. This study examines a unique, hand-collected dataset of 228 cryptocurrency exchanges operating between April 2011 and May 2024. Using various machine learning algorithms, we identify the key factors contributing to exchange shutdowns, with trading volume, exchange lifespan, and cybersecurity scores emerging as the most significant predictors. Since individual machine learning models often capture distinct data characteristics and exhibit varying error patterns, we employ a forecast combination approach by aggregating multiple predictive distributions. Specifically, we evaluate several specifications of the generalized linear pool (GLP), beta-transformed linear pool (BLP), and beta-mixture combination (BMC). Our findings reveal that the beta-transformed linear pool and the beta-mixture combination achieve the best performances, improving forecast accuracy by approximately 4.1% based on a robust H-measure, which effectively addresses the challenges of misclassification in imbalanced datasets. Full article
(This article belongs to the Special Issue Machine Learning Based Risk Management in Finance and Insurance)
►▼ Show Figures

Figure 1

Figure 1
<p>Receiver operating characteristic (ROC) curves for the five machine learning models. The x-axis represents the false positive rate (FPR), and the y-axis represents the true positive rate (TPR). The multiple intersections of these curves demonstrate that AUC alone may not capture the nuanced differences in performance, necessitating further evaluation metrics.</p> Full article ">Figure 2
<p>Feature Importance for the Two Best ML Models (CatBoost and Random Forest).</p> Full article ">

Other

Jump to: Research

34 pages, 4627 KiB  
Systematic Review
Challenges of Artificial Intelligence for the Prevention and Identification of Bankruptcy Risk in Financial Institutions: A Systematic Review
by Luis-Javier Vásquez-Serpa, Ciro Rodríguez, Jhelly-Reynaluz Pérez-Núñez and Carlos Navarro
J. Risk Financial Manag. 2025, 18(1), 26; https://doi.org/10.3390/jrfm18010026 - 10 Jan 2025
Viewed by 572
Abstract
The identification and prediction of financial bankruptcy has gained relevance due to its impact on economic and financial stability. This study performs a systematic review of artificial intelligence (AI) models used in bankruptcy prediction, evaluating their performance and relevance using the PRISMA and [...] Read more.
The identification and prediction of financial bankruptcy has gained relevance due to its impact on economic and financial stability. This study performs a systematic review of artificial intelligence (AI) models used in bankruptcy prediction, evaluating their performance and relevance using the PRISMA and PICOC frameworks. Traditional models such as random forest, logistic regression, KNN, and neural networks are analyzed, along with advanced techniques such as Extreme Gradient Boosting (XGBoost), convolutional neural networks (CNN), long short-term memory (LSTM), hybrid models, and ensemble methods such as bagging and boosting. The findings highlight that, although traditional models are useful for their simplicity and low computational cost, advanced techniques such as LSTM and XGBoost stand out for their high accuracy, sometimes exceeding 99%. However, these techniques present significant challenges, such as the need for large volumes of data and high computational resources. This paper identifies strengths and limitations of these approaches and analyses their practical implications, highlighting the superiority of AI in terms of accuracy, timeliness, and early detection compared to traditional financial ratios, which remain essential tools. In conclusion, the review proposes approaches that integrate scalability and practicality, offering predictive solutions tailored to real financial contexts with limited resources. Full article
(This article belongs to the Special Issue Machine Learning Based Risk Management in Finance and Insurance)
►▼ Show Figures

Figure 1

Figure 1
<p>Flowchart for systematic review.</p> Full article ">Figure 2
<p>The most commonly used techniques according to selected articles (see <a href="#jrfm-18-00026-t003" class="html-table">Table 3</a>).</p> Full article ">Figure 3
<p>Predictive performance of the models applied in the articles reviewed (see <a href="#jrfm-18-00026-t003" class="html-table">Table 3</a>); (<a href="#B2-jrfm-18-00026" class="html-bibr">Affes &amp; Hentati-Kaffel, 2019a</a>, <a href="#B3-jrfm-18-00026" class="html-bibr">2019b</a>; <a href="#B5-jrfm-18-00026" class="html-bibr">Aljawazneh et al., 2021</a>; <a href="#B12-jrfm-18-00026" class="html-bibr">Chandok et al., 2024</a>; <a href="#B13-jrfm-18-00026" class="html-bibr">Chen et al., 2021</a>; <a href="#B16-jrfm-18-00026" class="html-bibr">Da Silva Mattos &amp; Shasha, 2024</a>; <a href="#B19-jrfm-18-00026" class="html-bibr">Du et al., 2020</a>; <a href="#B22-jrfm-18-00026" class="html-bibr">Elhoseny et al., 2022</a>; <a href="#B28-jrfm-18-00026" class="html-bibr">Gabrielli et al., 2023</a>; <a href="#B29-jrfm-18-00026" class="html-bibr">Gajdosikova &amp; Valaskova, 2023</a>; <a href="#B30-jrfm-18-00026" class="html-bibr">Garcia, 2022</a>; <a href="#B31-jrfm-18-00026" class="html-bibr">Gavurova et al., 2022</a>; <a href="#B34-jrfm-18-00026" class="html-bibr">Hamdi et al., 2024</a>; <a href="#B35-jrfm-18-00026" class="html-bibr">Hosaka, 2019</a>; <a href="#B37-jrfm-18-00026" class="html-bibr">Idhmad et al., 2024</a>; <a href="#B41-jrfm-18-00026" class="html-bibr">Jabeur &amp; Serret, 2023</a>; <a href="#B42-jrfm-18-00026" class="html-bibr">Jain et al., 2021</a>; <a href="#B43-jrfm-18-00026" class="html-bibr">Jencova et al., 2021</a>; <a href="#B45-jrfm-18-00026" class="html-bibr">Khan et al., 2024</a>; <a href="#B47-jrfm-18-00026" class="html-bibr">Lukason &amp; Andresson, 2019</a>; <a href="#B50-jrfm-18-00026" class="html-bibr">Muslim &amp; Dasril, 2021</a>; <a href="#B53-jrfm-18-00026" class="html-bibr">Noh, 2023</a>; <a href="#B54-jrfm-18-00026" class="html-bibr">Oberoi &amp; Banerjee, 2023</a>; <a href="#B55-jrfm-18-00026" class="html-bibr">Pamuk et al., 2021</a>; <a href="#B57-jrfm-18-00026" class="html-bibr">Pavlicko et al., 2021</a>; <a href="#B60-jrfm-18-00026" class="html-bibr">Radovanovic &amp; Haas, 2023</a>; <a href="#B65-jrfm-18-00026" class="html-bibr">Shetty et al., 2022</a>; <a href="#B66-jrfm-18-00026" class="html-bibr">Shrivastav &amp; Ramudu, 2020</a>; <a href="#B67-jrfm-18-00026" class="html-bibr">Siswoyo et al., 2022</a>; <a href="#B78-jrfm-18-00026" class="html-bibr">Valverde &amp; Ortiz, 2022</a>; <a href="#B79-jrfm-18-00026" class="html-bibr">Vochozka et al., 2020</a>; <a href="#B82-jrfm-18-00026" class="html-bibr">X. Wang et al., 2023</a>; <a href="#B84-jrfm-18-00026" class="html-bibr">Xhindi &amp; Shestani, 2020</a>).</p> Full article ">Figure 4
<p>Datasets and number of variables used in the articles reviewed (see <a href="#jrfm-18-00026-t003" class="html-table">Table 3</a>); (<a href="#B2-jrfm-18-00026" class="html-bibr">Affes &amp; Hentati-Kaffel, 2019a</a>, <a href="#B3-jrfm-18-00026" class="html-bibr">2019b</a>; <a href="#B5-jrfm-18-00026" class="html-bibr">Aljawazneh et al., 2021</a>; <a href="#B12-jrfm-18-00026" class="html-bibr">Chandok et al., 2024</a>; <a href="#B13-jrfm-18-00026" class="html-bibr">Chen et al., 2021</a>; <a href="#B16-jrfm-18-00026" class="html-bibr">Da Silva Mattos &amp; Shasha, 2024</a>; <a href="#B19-jrfm-18-00026" class="html-bibr">Du et al., 2020</a>; <a href="#B22-jrfm-18-00026" class="html-bibr">Elhoseny et al., 2022</a>; <a href="#B29-jrfm-18-00026" class="html-bibr">Gajdosikova &amp; Valaskova, 2023</a>; <a href="#B30-jrfm-18-00026" class="html-bibr">Garcia, 2022</a>; <a href="#B31-jrfm-18-00026" class="html-bibr">Gavurova et al., 2022</a>; <a href="#B34-jrfm-18-00026" class="html-bibr">Hamdi et al., 2024</a>; <a href="#B35-jrfm-18-00026" class="html-bibr">Hosaka, 2019</a>; <a href="#B37-jrfm-18-00026" class="html-bibr">Idhmad et al., 2024</a>; <a href="#B41-jrfm-18-00026" class="html-bibr">Jabeur &amp; Serret, 2023</a>; <a href="#B42-jrfm-18-00026" class="html-bibr">Jain et al., 2021</a>; <a href="#B43-jrfm-18-00026" class="html-bibr">Jencova et al., 2021</a>; <a href="#B45-jrfm-18-00026" class="html-bibr">Khan et al., 2024</a>; <a href="#B47-jrfm-18-00026" class="html-bibr">Lukason &amp; Andresson, 2019</a>; <a href="#B50-jrfm-18-00026" class="html-bibr">Muslim &amp; Dasril, 2021</a>; <a href="#B53-jrfm-18-00026" class="html-bibr">Noh, 2023</a>; <a href="#B54-jrfm-18-00026" class="html-bibr">Oberoi &amp; Banerjee, 2023</a>; <a href="#B55-jrfm-18-00026" class="html-bibr">Pamuk et al., 2021</a>; <a href="#B57-jrfm-18-00026" class="html-bibr">Pavlicko et al., 2021</a>; <a href="#B60-jrfm-18-00026" class="html-bibr">Radovanovic &amp; Haas, 2023</a>; <a href="#B64-jrfm-18-00026" class="html-bibr">Shah et al., 2022</a>; <a href="#B65-jrfm-18-00026" class="html-bibr">Shetty et al., 2022</a>; <a href="#B66-jrfm-18-00026" class="html-bibr">Shrivastav &amp; Ramudu, 2020</a>; <a href="#B67-jrfm-18-00026" class="html-bibr">Siswoyo et al., 2022</a>; <a href="#B78-jrfm-18-00026" class="html-bibr">Valverde &amp; Ortiz, 2022</a>; <a href="#B79-jrfm-18-00026" class="html-bibr">Vochozka et al., 2020</a>; <a href="#B82-jrfm-18-00026" class="html-bibr">X. Wang et al., 2023</a>; <a href="#B84-jrfm-18-00026" class="html-bibr">Xhindi &amp; Shestani, 2020</a>).</p> Full article ">Figure 5
<p>Countries of the banks and companies studied according to the selected articles (see <a href="#jrfm-18-00026-t003" class="html-table">Table 3</a>).</p> Full article ">Figure 6
<p>Type of entities studied on the risk of bankruptcy according to selected articles.</p> Full article ">Figure 7
<p>The most commonly used variables according to the literature reviewed.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop