Elitist-opposition-based artifcial electric feld algorithm for higher-order neural network optimization and fnancial time series forecasting

This study attempts to accelerate the learning ability of an artifcial electric feld algorithm (AEFA) by attributing it with two mechanisms: elitism and oppositionbased learning. Elitism advances the convergence of the AEFA towards global optima by retaining the fne-tuned solutions obtained thus far, and opposition-based learning helps enhance its exploration ability. The new version of the AEFA, called elitist opposi‑ tion leaning-based AEFA (EOAEFA), retains the properties of the basic AEFA while tak‑ ing advantage of both elitism and opposition-based learning. Hence, the improved version attempts to reach optimum solutions by enabling the diversifcation of solu‑ tions with guaranteed convergence. Higher-order neural networks (HONNs) have single-layer adjustable parameters, fast learning, a robust fault tolerance, and good approximation ability compared with multilayer neural networks. They consider a higher order of input signals, increased the dimensionality of inputs through func‑ tional expansion and could thus discriminate between them. However, determining the number of expansion units in HONNs along with their associated parameters (i.e., weight and threshold) is a bottleneck in the design of such networks. Here, we used EOAEFA to design two HONNs, namely, a pi-sigma neural network and a functional link artifcial neural network, called EOAEFA-PSNN and EOAEFA-FLN, respectively, in a fully automated manner. The proposed models were evaluated on fnancial time-series datasets, focusing on predicting four closing prices, four exchange rates, and three energy prices. Experiments, comparative studies, and statistical tests were conducted to establish the efcacy of the proposed approach.