Building reproducible tools for quantitative research, causal inference, and AI applications.
关注量化研究、因果推断与 AI 应用，把方法做成可以运行、检查和复现的项目。
A Python research pipeline connecting factor evaluation, walk-forward modeling, portfolio construction, transaction costs, and HTML reports. Includes a FastAPI service and a Streamlit dashboard.
Start here: Documentation · Computed sample · Source & tests
The bundled sample data is synthetic; its results demonstrate the workflow and do not establish a tradable edge.
An interactive simulation lab for high-dimensional covariate adjustment, causal estimation, and robust asset allocation.
Explore: Browser demo · Repository
Experiments use simulated data and depend on the chosen data-generating assumptions.
A factor research workflow with point-in-time feature alignment, purged out-of-sample evaluation, portfolio accounting, and browser reports.
Explore: Live report · 中文文档 · Methodology
The default run uses synthetic data. Complete point-in-time financial statement normalization for real-market experiments is still in progress.
| Project | Focus |
|---|---|
| Interval Financial Risk | Experiment report comparing point and distributional features, with temporal validation and downloadable predictions. |
| Investor Network GNN | Three-seed benchmark: fixed-checkpoint graph ablations, saved predictions and independent metric checks. |
| WeCom Agent Platform | Document retrieval and query workflows with a Python backend and React interface. |
Personal AI Chat also provides a local simulated chat mode and a separately configured private model connection.
Python · NumPy · pandas · scikit-learn · PyTorch · FastAPI · TypeScript · React
I focus on explicit data provenance, reproducible experiments, baseline comparisons, and tests that check model and application behavior. Each repository documents its setup and current limitations.