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.
Investigate whether transaction groups and interpretable rules, including rules proposed by language models, improve future fraud detection beyond a LightGBM baseline.
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.
Built with the Universal theme for Hugo.
