MO-RSAR: Multi-Objective Hyperparameter Optimization of RSAR for Financial Time-Series Forecasting

Abstract

This paper empirically compares four architectures for financial time-series forecasting: LSTM, CNN, the original Regularized Self-Attention Regression (RSAR) model, and a multiobjective optimized RSAR variant, denoted MO-RSAR, obtained using the Non-dominated Sorting Genetic Algorithm II (NSGA-II). The models are evaluated on six datasets covering Forex, equity index and cryptocurrency markets, for short and long horizons. All models share a common preprocessing pipeline and evaluation framework and are assessed using standard error metrics, with emphasis on Mean Absolute Percentage Error (MAPE). MO-RSAR yields the lowest average prediction error across all datasets and provides significant gains for longer, more volatile horizons, while simpler architectures remain competitive for short-term forecasts. The key methodological contribution is the first empirical integration of the RSAR architecture with NSGA-IIbased multi-objective hyperparameter optimization for financial time-series forecasting. The proposed framework treats RSAR configuration as a bi-objective search over accuracy and generalization (via the train-validation gap), and evaluates the resulting model under a unified protocol across heterogeneous markets and horizons.