Upload README.md with huggingface_hub

README.md

@@ -14,14 +14,29 @@ license: mit
 
 ## Per-Stock Models
 
-**89 individual per-stock models**, each under `per_stock/{SYMBOL}.onnx`.
+**{len(per_stock_metrics)} individual per-stock models**, each under `per_stock/{SYMBOL}.onnx`.
 
-- **Architecture**: iTransformer with RevIN (427,641 parameters each)
-- **Input**: 60 days x 83 features (OHLCV technicals + macro)
+- **Architecture**: iTransformer with RevIN (433,274 parameters each)
+- **Input**: 60 days x 126 features (OHLCV technicals + macro + relative strength)
 - **Output**: 60-day forward return forecast
 - **Training**: Walk-forward validation (70/15/15), HuberLoss(delta=0.02)
-- **Average 7-day directional accuracy**: 51.3%
-- **Average 30-day directional accuracy**: 55.8%
+- **Average 7-day directional accuracy**: 51.8%
+- **Average 30-day directional accuracy**: 56.8%
+
+## v7.0 Features (126 total — includes FRED macro)
+
+- 83 original: OHLCV technicals, momentum, volume, volatility, statistics, calendar, macro
+- 4 relative strength: stock vs SPY returns (5/20/60d), SPY correlation
+- 3 cross-asset: VIX correlation, rolling beta, volume-price correlation
+- 4 advanced volume: MFI, A/D line, VWAP deviation, Force Index
+- 5 price structure: range position, ATR ratio, consecutive days, candle body
+- 5 statistical regime: Hurst exponent, Parkinson/GK volatility, consistency, tail ratio
+- 4 intermarket: SPY momentum, gold/oil ratio, DXY-VIX interaction
+- 3 sector ETF: stock vs sector ETF returns (5/20d), sector correlation
+- 4 credit market: HYG/TLT returns, credit spread proxy, HYG-SPY divergence
+- 1 VIX term structure: VIX9D/VIX short-term fear ratio
+- 2 industry commodity: per-stock commodity correlation and return
+- 2 intermarket extended: copper/gold ratio change, BTC sentiment
 
 ## Usage
 
@@ -32,7 +47,7 @@ import numpy as np
 # Load per-stock model
 session = ort.InferenceSession("per_stock/AAPL.onnx")
 
-# features shape: (1, 60, 83)
+# features shape: (1, 60, 126)
 output = session.run(None, {"features": features})[0]
 # output shape: (1, 60) — predicted returns
 ```