Empirical Asset Pricing via Machine Learning: Evidence from Indian Equity Markets
“A three-layer neural network (NN3) delivers the strongest pooled out-of-sample R 2 (0.55% per month), while tree-based ensembles (Random Forest, GBRT, XGBoost) deliver the weakest statistical predictability among the fourteen models, with Random Forest producing a negative out-of-sample R 2.”
AssetEquitiessingle stocks
StrategyMachine learningmomentum
TechniqueFeedforward networktree ensemble
GeographyGlobalIndia
Also stated: 2000–2024, Sharpe ratio, Drawdown, Long-short, Price and volume, out-of-sample test, universe of 375 stocks
Missing from abstract: benchmark, costs, multiple testing
Institutional-grade audit of this strategy.
£5 — Request the audit- Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
- Reproduction code integratable into Bloomberg, IBKR, etc.
- Bias-free datasets for backtesting included
- Delivered in 2 working days
The paper's neighbourhoodMachine learning return prediction by year
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
| Similar papers | citation | same method | same asset | same authors | |
|---|---|---|---|---|---|
| Spatiotemporal Signals in Residuals: A Two-Stage Boosting Graph Neural Network for Stock Return Prediction by Liu et al. | 2026 | ||||
| Machine Learning for Cross-Sectional Return Prediction: A Comparative Study of US and Indian Equities by Khatu | 2026 | ||||
| Stock Return Prediction Guided by a Revised Random Walk Hypothesis: Adaptive Information Smoothing and Signed Correlation-Aware TimeMixing by Seo and Yang | 2026 | ||||
| Visualizing Income Statements by Garfinkel et al. | 2026 | ||||
| Machine Learning-Based Stock Return Prediction for NEPSE: Do Global Feature Sets Outperform Traditional Technical Indicators in an Emerging, Illiquid Frontier Market? An Independent Study Submitted in Partial Fulfilment of the Requirements for the Bachelor of Management Studies (BMS) by Basnet | 2026 |