Akademik Veri Yönetim Sistemi
Progress in Artificial Intelligence, 2025 (ESCI)
Developing a revolutionary silver price forecasting model using multi-objective optimization, drawing inspiration from jellyfish hunting activities is a new economic advancement. This study Improve economic decision-making by using a dynamic strategy that takes into account the complexities of market fluctuations. Consequently, the demand for green energy systems will rise, leading to a corresponding increase in the need for silver in their manufacturing. Hence, fluctuations in silver prices have a substantial influence on economic decisions, planning, and expenses. The primary objective of this work is to analyze and develop a reliable forecasting model for predicting silver prices. A modern meta-heuristic method called the jellyfish searching optimizer algorithm (JSO) is used in this study to train and learn from the support vector regression (SVR), random forest, multilayer perceptron neural network (MLPNN), generalized feed forward neural network (GFFNN), bidirectional recurrent neural network (BRNN), and radial basis function (RBF) algorithms. The results of the proposed model are compared to the base models, including the MLPNN, GFFNN, BRNN, RBF, SVR, and RF. Moreover, the proposed JSO-RF model demonstrates an improvement in the forecasting accuracy obtained from the classic MLPNN, GFFNN, BRNN, RBF, SVR, and RF models by 49.35, 49.81, 46.72, 51.33, 49.44, 50.57, 47.51, 46.91, and 47.16% decrease in weighted mean absolute percentage error, respectively. The techniques developed in this study holds significant potential for the strategic economic planning of sustainable energy and electronic industries.