Patel J.Gunes P.Ertugrul S.Sayar A.Benli H.Makaroglu D.Cakar T.2026-03-052026-03-0520252521-1641https://doi.org/10.1109/UBMK67458.2025.11206981https://hdl.handle.net/20.500.11779/3233Stock return forecasting is a challenging task due to the complex, nonlinear, and volatile nature of financial markets. In this paper, we propose a comprehensive deep learning framework that integrates: a two-layer Long Short-Term Memory (LSTM) network augmented with a learnable attention mechanism, a dual-head output for simultaneous regression of next-day returns and classification of price direction, with an extensive suite of technical and macro-financial features. Our feature set comprises lagged log-returns, trend indicators (simple and exponential moving averages), momentum oscillators (RSI, MACD), volatility measures (rolling variance and GARCH conditional volatility), price bands (Bollinger Bands, Donchian channels), volume metrics (On-Balance Volume, Volume Rate of Change), Hidden Markov Model regime states, market index returns, and calendar effects. We train and validate the model using a rolling-window cross-validation scheme with early stopping and hyperparameter tuning to ensure temporal robustness. Empirical results on a large multi-stock dataset demonstrate that our attention-enhanced, dual-task LSTM outperforms single-task LSTMs and traditional machine learning benchmarks, achieving lower forecasting error and more stable generalization. © 2025 IEEE.eninfo:eu-repo/semantics/closedAccessAttention-Enhanced LSTMDual-Task LearningFinancial Feature EngineeringRisk-Adjusted BacktestingRolling-Origin Cross-ValidationStock EmbeddingConference Object10.1109/UBMK67458.2025.112069812-s2.0-105030880427