DIRECTIONAL PREDICTION OF INDIAN THEMATIC EQUITY INDICES USING MACHINE LEARNING ENSEMBLE CLASSIFIERS
A 2026 paper by Arora on machine learning return prediction in real estate, using tree ensembles: the abstract mentions a Sharpe ratio, alpha, excess returns, a benchmark and an out-of-sample test and leaves out transaction costs, multiple testing and the size of the universe.
“Results confirm a robust Horizon Effect: 1-day accuracy approximates the random walk baseline (50–56%), while GB achieves 90.8–95.1% accuracy at the 20-day horizon, outperforming Logistic Regression by 22–32 percentage points across all indices.”
AssetReal estateindices
StrategyMachine learning
TechniqueTree ensemblelinear factor model
GeographyIndia
Also stated: Sharpe ratio, Alpha, Excess return, Long-only, Price and volume, benchmark, out-of-sample test
Missing from abstract: costs, multiple testing, universe
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.