What question did this study set out to answer?

The aim is to establish a rigorous benchmark for predicting short-horizon equity returns and volatilities without model performance inflation.

June 19, 2026Engineering ReportsOpen Access

Audit‐Ready Machine Learning for Short‐Horizon Equity Prediction: A Dual‐Target Benchmark With Fold‐Isolated Preprocessing

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates equity return and volatility predictions in US mega-cap equities, suggesting improvements in forecasting techniques.

The aim is to establish a rigorous benchmark for predicting short-horizon equity returns and volatilities without model performance inflation.
Introduces a leakage-controlled, expanding-window walk-forward benchmark using daily OHLCV data from 2010–2026.
Assesses multiple model families including naive baselines, Ridge regression, Random Forest, and others across 41 causal folds.
Incorporates fold-isolated preprocessing to eliminate data leakage.
Signed-return forecasting remains statistically indistinguishable from naive baselines across all models (p>0.05).
Random Forest model achieves a 7.19% reduction in RMSE for volatility proxy compared to rolling baselines.
SHAP analyses indicate that recent volatility, range, and liquidity features are critical for short-horizon predictions.

Masum et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

June 19, 2026Engineering ReportsOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates equity return and volatility predictions in US mega-cap equities, suggesting improvements in forecasting techniques.

The aim is to establish a rigorous benchmark for predicting short-horizon equity returns and volatilities without model performance inflation.
Introduces a leakage-controlled, expanding-window walk-forward benchmark using daily OHLCV data from 2010–2026.
Assesses multiple model families including naive baselines, Ridge regression, Random Forest, and others across 41 causal folds.
Incorporates fold-isolated preprocessing to eliminate data leakage.
Signed-return forecasting remains statistically indistinguishable from naive baselines across all models (p>0.05).
Random Forest model achieves a 7.19% reduction in RMSE for volatility proxy compared to rolling baselines.
SHAP analyses indicate that recent volatility, range, and liquidity features are critical for short-horizon predictions.

Masum et al. (2026) studied this question.

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark