Predicting Stock Market Prices Using a Hybrid of High-Order Neural Networks and Barnacle Mating Optimization

Predicting stock market movements presents a formidable challenge due to the inherent nonlinearity and ever-changing nature of financial markets. In this research endeavor, we employ an innovative approach, harnessing the power of an evolutionary algorithm called barnacle mating optimization (BMO), to fine-tune the optimal parameters of a sophisticated neural network known as the Pi-Sigma neural network (PSNN). This intricate optimization process results in the development of a hybrid model, aptly named BMO-PSNN. We put BMO-PSNN to the test by utilizing it for predicting the closing prices of five widely tracked stock indices. In order to provide a comprehensive comparison, we also implement the traditional gradient descent (GD) optimization technique to train the PSNN network for the same predictive task. The performance evaluation is carried out using the average percentage error (APE) metric. Remarkably, the results conclusively demonstrate that BMO-PSNN outshines GD-PSNN in its ability to make more accurate predictions, underscoring the effectiveness of the evolutionary BMO algorithm in tackling the complexities of stock market forecasting.