Instructions to use Tjgguy12/forex-6pair-1d-quant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use Tjgguy12/forex-6pair-1d-quant with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("Tjgguy12/forex-6pair-1d-quant", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Forex 6-Pair 1D Quant โ EURUSD 35% GBPUSD 25% USDJPY 20% AUDUSD 10% USDCAD 10%
Edges: EURUSD mean reversion, GBPUSD vol clustering, USDJPY vol+carry, AUDUSD mean reversion, USDCAD oil beta. Tail risk USDTRY/ZAR excluded. Do NOT trade USDHKD/EURDKK.
Training: 5y yfinance (6150 rows, 1300 per pair), Voting XGB+LGBM, 3 folds, 1d embargo. Result: Mean IC -0.012, Ann -6.94% to -1.89% โ negative (worse than random). Status: Experimental, NOT production. Needs longer history (2004 Kaggle daily) + proper session features + FinBERT.
Live test 2026-09-09:
- EURUSD 1.16387 DOWN P_up 0.297 exp -0.034%
- GBPUSD 1.35553 DOWN 0.213 -0.026%
- USDJPY 153.54 DOWN 0.398 +0.115%
- AUDUSD 0.72218 DOWN 0.348 +0.018%
- USDCAD 1.3806 DOWN 0.429 +0.047%
Kaggle: https://www.kaggle.com/code/maxvwede/forex-6pair-1d-quant-eur-gbp-jpy Portfolio: 35/25/20/10/10 weighted daily rets, 1bp spread.
Next: Retrain with 2004-2026 Kaggle daily (20y) + London/Tokyo session + oil beta for USDCAD.
- Downloads last month
- -