This repository has two tests that comply with the Computer Vision and Machine Learning expertise testing procedures. Each test has its own set of files, parameters and strategies to be solved. Therefore, choose the most appropriate solving method in each situation.
The following tests are given:
- Document Cleanup
- Fraud Detection
The instructions to each problem are described in separated README files in each folder.
Please, develop a script or program using the programming language of your choice to solve each of those Computer Vision and Machine Learning problems. We are aware of the difficulty associated with each problem, but all the creativeness, reasoning strategy and accuracy will be used to evaluate the candidate performance.
We expect that a solution could be reasonably achieved within 2 weeks (14 running days), so be free to use the time as best as possible.
All the datasets are located into a single compressed file in this link.
Note that the file is quite big (~1 Gb), but we believe that a few minutes could deal with it
Fork this project and create a branch with your first + last name on it. For instance, a branch naming "Antonio Silva" will define that the candidate with the same name is uploading the code with the solution for each test. Please, give the scripts and code in separate folders (with the same name as the provided file folders) to facilitate our analysis. Also, we expect that the candidate can explain the procedure and strategy adopted by using a lot of commentaries or even a separated README file. Be free to choose what is more suitable for you, but keep it simple and clear to understand.
After all the analysis and coding being done, create a pull request (PR) in this repository.
As an extra help, use the following checklist to verify if everything is ok:
- Downloaded all the test files using the link.
- Create a suitable solution for each test, e.g. using scripts, open-source libraries, own-code solutions, etc. Consider we follow your instructions to run your code and look the outcome.
- Make commentaries or auxiliary documentation files (e.g. README files) to assist the interpretation of your solutions.
- Save the resulting code, scripts, etc on separated folders with complies with the same name as the input dataset (just to help us 👍)
- Prepare the commits on the PR using the branch with your first + last name in it.
- Submit the PR! (fingers crossed 😊)