2019-2020 Projects

· by [Fabrice Popineau] · Read in about 2 min · (228 words) ·

These projects have been worked out between 2019/10/15 and 2020/03/31. They have been undertaken by Supélec 3rd year students in the Computer Science major.

Project 1 - Fraud and Explainability

By Camille Michel and Emmanuelle Salin

The goal of this project was to investigate the current techniques for explaining machine learning models, especially those suitable for fraud detection. The LIME and SHAP techniques have been studied when applied to random forests and multilayer perceptrons.


Project 2 - Fraud detection by graphs

By Roméo Leylekian and Nicolas Nerriennet

The goal of this project was to investigate the new techniques of machine learning applied to graphs. Several ways of modeling credit card transactions have been tested, together with algorithms.


Project 3 - Metrics adapted to automated trading

By Hugo Kyhm and Matthieu Nogatchewsky

Litterature about machine learning applied to automated trading most often reports results using a very crude metric: . The goal of this project was to investigate if it is possible to build a metric which would better reflect the results of backtesting.


Project 4 - Automated playlists

By Henri Chabert, Clara Samuel and Coline Therial

Digital music services need to build personalized playlists for their customers. Assembling such playlists when there is a database of 40 millions of titles is tedious. This project investigated some research lines in order to solve this task.