Stock Daily Sentiment (Up/Down)

Predicts whether next-day close-to-close return is positive (1) or not (0) using daily OHLCV-derived features (returns/volatility, RSI(14), MACD, Bollinger %B, SMA ratios) plus SPY daily return.

Holdout metrics:

  • ACC β‰ˆ 0.52
  • AUC β‰ˆ 0.523
  • F1 β‰ˆ 0.68

Usage (programmatic)

from huggingface_hub import hf_hub_download
import skops.io as sio

arts = sio.load(hf_hub_download(
    repo_id="jacobre20/stock-sentiment-daily-v1",
    filename="model.skops"
))
model = arts["model"]
feature_cols = arts["feature_cols"]

# X must be a DataFrame with the same feature columns in 'feature_cols'
# proba = model.predict_proba(X[feature_cols].values)[:, 1]
# pred  = (proba >= 0.5).astype(int)




Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Space using jacobre20/stock-sentiment-daily-v1 1