TongjiFinLab/FinTSB

FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting (ICAIF'25 Workshop Best Paper)

45
/ 100
Emerging

This project helps quantitative analysts and financial researchers accurately evaluate their stock market prediction models. It takes raw financial time series data and processes it through standardized benchmarks, providing performance metrics, backtesting results, and visualizations. This allows users to understand how their models perform across diverse market conditions and compare them against established methods.

121 stars. No commits in the last 6 months.

Use this if you need a reliable and standardized way to test and compare financial time series forecasting models for stock movement prediction.

Not ideal if you are looking for an out-of-the-box trading system or a tool for general time series analysis outside of financial markets.

quantitative-finance financial-modeling stock-forecasting algorithmic-trading-research market-analysis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

121

Forks

20

Language

Python

License

GPL-3.0

Last pushed

Aug 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TongjiFinLab/FinTSB"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.