A Quantum-Inspired Evolutionary Learning Process to Design Dilation-Erosion Perceptrons for Financial Forecasting

Abstract

Financial forecasting problems are rather difficult to be solved due to many complex features present in these time series. Several techniques have been proposed in the literature to solve this kind of problem. However, a dilemma arises from them, known as random walk dilemma, where the forecasts generated show a characteristic one step delay with respect to the real time series data. In this sense, this work presents a quantum-inspired evolutionary learning process to design the dilation-erosion perceptron (DEP) in order to overcome the random walk dilemma for financial forecasting. Furthermore, an experimental analysis is presented using the Dow Jones Industrial Average Index, where five well-known performance metrics and an evaluation function are used to assess forecasting performance.