Grid search-based LSTM hyperparameter options.

This study introduces a deep learning-based framework for portfolio optimization tailored to different investor risk preferences. We combine two prediction models, Long Short-Term Memory (LSTM) and One-Dimensional Convolutional Neural Network (1D-CNN), with three portfolio frameworks: Mean-Variance with Forecasting (MVF), Risk Parity Portfolio (RPP), and Maximum Drawdown Portfolio (MDP). Each framework represents a distinct risk profile: return-seeking, moderate-risk and conservative. The dataset is constructed from daily returns of VN-100 stocks in Vietnam, covering the period from 2017 to 2024. Forecasts from the deep learning models are integrated into each optimization approach. Results from the 2023–2024 test period showed that LSTM outperforms 1D-CNN in both accuracy and stability. Portfolios using LSTM achieved better performance. LSTM+MVF delivers the best risk-adjusted returns, while LSTM+MDP achieves the highest total return. The study highlights the value of aligning predictive models with appropriate optimization strategies for improved investment outcomes. Future work may include other asset classes, transaction cost modeling, and dynamic rebalancing. Combining deep learning with macroeconomic or alternative data could also improve forecasting and portfolio outcomes.