chirindaopensource/reasoning_time_series_financial_technical_analysis

End-to-End Python implementation of Koa et al.'s (2025) novel self-explaining quantitative framework. It combines cross-modal transformers, Time-GRPO reinforcement learning, and classifier-free guidance. Trains LLMs to perform financial technical analysis using LoRA fine-tuning. Includes backtesting with Markowitz portfolio optimization.

15
/ 100
Experimental
No Package No Dependents
Maintenance 6 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/chirindaopensource/reasoning_time_series_financial_technical_analysis"

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