LearnFinance PatchTST Model - v2026-02-27-931afeb6338a
OHLCV 5-channel PatchTST transformer model for predicting weekly stock returns.
Model Details
- Version: v2026-02-27-931afeb6338a
- Model Type: PatchTST (Patch Time Series Transformer)
- Training Window: 2016-01-01 to 2026-02-27
- Symbols: 207 stocks
Input Channels (11 total)
- OHLCV log returns (5): open, high, low, close, volume
- News sentiment (1)
- Fundamentals (5): gross_margin, operating_margin, net_margin, current_ratio, debt_to_equity
Metrics
- Train Loss: 0.1433181384036058
- Validation Loss: 0.18421696890381317
- Baseline Loss: 0.18782168626785278
Usage
from brain_api.storage.huggingface import PatchTSTHuggingFaceModelStorage
storage = PatchTSTHuggingFaceModelStorage(repo_id="hajirazin/learnfinance-models-patchtst-india")
artifacts = storage.download_model(version="v2026-02-27-931afeb6338a")
- Downloads last month
- 40
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support