nuglifeleoji/Factor-Research
A quantitative finance research project using LSTM+ResNet deep learning models to predict stock returns with a 0.06476 Information Coefficient.
Not currently ranked — collecting fresh signals.
star history
This project implements a complete quantitative research pipeline using machine learning for alpha factor generation and stock return prediction. It features a comprehensive factor library with systematic feature selection reducing 100+ candidates to 85 high-quality factors, multiple deep learning architectures (LSTM, ResNet, Transformer), automated hyperparameter tuning via Optuna, and a backtesting framework. The best-performing LSTM+ResNet model achieved a 72% performance improvement over linear regression baselines.
Frequently asked
- What is nuglifeleoji/Factor-Research?
- A quantitative finance research project using LSTM+ResNet deep learning models to predict stock returns with a 0.06476 Information Coefficient.
- Is Factor-Research open source?
- Yes — nuglifeleoji/Factor-Research is an open-source project tracked on heatdrop.
- What language is Factor-Research written in?
- nuglifeleoji/Factor-Research is primarily written in Jupyter Notebook.
- How popular is Factor-Research?
- nuglifeleoji/Factor-Research has 408 stars on GitHub.
- Where can I find Factor-Research?
- nuglifeleoji/Factor-Research is on GitHub at https://github.com/nuglifeleoji/Factor-Research.