| This study investigates the predictive and allocative performance of multiple machine learning (ML) models in the context of quarterly equity return forecasting and portfolio optimization. Using exclusively publicly accessible data from the AlphaVantage API, the research aims to provide a transparent and reproducible comparison of ML-based predictive frameworks under conditions that approximate the informational environment of a real-world investor. The analysis incorporates twenty fundamental financial ratios capturing profitability, valuation, leverage, liquidity, and efficiency dimensions, which serve as explanatory variables for predicting three-month ahead stock returns. To ensure methodological rigor, the study employs a rolling-window design with 12–20 quarter training periods and 4-quarter out-of-sample testing windows, combined with realistic two-month reporting lags to mitigate look-ahead bias. The evaluated models include Linear Regression, Ridge Regression with cross-validated regularization, Random Forest, XGBoost, and a Stacked Ensemble integrating these approaches. Portfolios are constructed by selecting the top 5–20% of predicted stocks within each sector, with both equal-weighted and later prediction-weighted allocation schemes. Empirical findings demonstrate that nonlinear ensemble techniques, particularly XGBoost, significantly improve risk-adjusted performance relative to linear baselines and exhibit robust results across multiple concentration thresholds. The paper concludes that methodological transparency, realistic data assumptions, and adaptive allocation design are essential for translating machine learning forecasts into economically meaningful investment strategies. Future research directions include integrating macroeconomic and sentiment-based signals, adopting more models, and applying advanced allocation methods such as Black–Litterman optimization to further enhance robustness and capital efficiency. |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.