This project compares language model agents, random search and genetic search for financial factor discovery, isolating the contribution of experimental memory under a common evaluation budget.
This project investigates whether financial news sentiment extracted by large language models can improve trading signals, with an emphasis on Apple stock, news timing and rigorous backtesting.
This MMF project studies uncertainty estimates for transformer models, initially on tabular classification, with potential applications to the reliability of trading predictions.
Design and compare decision trees with multiple-variable conditions for interpretable prediction on trading or fraud data.
This project explores the use of anomaly detection techniques, such as One-Class SVM, to identify the conditions under which algorithmic trading strategies are likely to succeed, ensuring their applicability and extending the approach to portfolio-wide strategy optimization.
The Junior Conference on DataScience and Engeneering 2022 (JDSE) took place on september 15-16, on the Polytechnique campus (Palaiseau).
Hugo Thimonier has the opportunity to present “TracInAD: Measuring Influence for Anomaly Detection” to the audience.
Marc Velay won the best poster contest with his poster about “Robustness Analysis of Deep RL for Portfolio Selection”.
Learning reward functions from portfolio allocation strategies and evaluating inverse reinforcement learning for automated trading.
Inverse Reinforcement Learning for portfolio allocation.
Built with the Universal theme for Hugo.
