<![CDATA[Neural Networks (NNs) are extensively used in time series forecasting due to their ability to learn nonlinear and complex temporal relationships. However, NN performance is frequently limited by training challenges, including slow convergence and suboptimal parameter optimization. This study aims to systematically examine the role of the Modified Orca Predation Algorithm (MOPA) in enhancing neural network performance for time series forecasting, particularly in comparison with other metaheuristic optimization approaches. This research employed a qualitative method using a Systematic Literature Review (SLR) approach. Relevant journal and conference articles published between 2015 and 2025 were collected from reputable scientific databases. The selected studies were analyzed thematically and bibliometrically using VOSviewer to identify research trends, application domains, and performance characteristics of MOPA-based neural network optimization. The results indicate that the integration of MOPA into neural network training consistently improves convergence speed, forecasting accuracy, and model stability across various application domains. Compared to conventional optimization methods, MOPA demonstrates superior capability in handling nonlinear and volatile time series data, particularly in energy forecasting, financial time series analysis, and climate-related prediction. The findings also reveal that MOPA-based optimization contributes to better generalization performance by reducing prediction error and output variance. This study provides a structured synthesis of recent research on MOPA-enhanced neural networks and contributes to the understanding of metaheuristic optimization strategies in time series forecasting. The results serve as a reference for researchers in selecting effective optimization methods for neural network-based forecasting models.]]>
