A broad range of nature inspired optimization techniques are proposed and applied to forecast stock market. They performed notably differently across the stock market datasets. This article attempts to construct a cooperative optimization algorithm (COA) framework as an alternative of employing solitary algorithm. The COA considers genetic algorithm and chemical reaction optimization as constituent techniques. The framework executes each constituent algorithm with a fraction of the whole computation time budget and encourages interaction between them so that they can be benefited from each other. A component technique compares its best result so far obtained with the best established result from the other at regular interval. If the quality of the established result is better than its own best result, it replaces its solution by the received one. The COA is used to adjust the weight and bias vectors of two higher order neural networks such as Pi-Sigma neural network (PSNN) and functional link artificial neural network (FLANN) separately hence, forming two COA-HONN hybrid models. The models are evaluated on forecasting daily closing prices of five real stock datasets. The experimental results confirm that the COA approach enhances the prediction accuracy over individual algorithm. We conducted the Deibold-Mariano test to check the statistical significance of the proposed models, and it was found to be significant. Hence, the proposed approach can be used as a promising tool for stock market forecasting.
YAPAY SİNİR AĞLARI İLE BORSA ENDEKSİ TAHMİNİ - FORECASTING STOCK MARKET INDEX WITH ARTIFICIAL NEURAL NETWORKS
