A robust automatic phase-adjustment method for financial forecasting

In this work we present the robust automatic phase-adjustment (RAA) method to overcome the random walk dilemma for financial time series forecasting. It consists of a hybrid model composed of a qubit multilayer perceptron (QuMLP) with a quantum-inspired evolutionary algorithm (QIEA), which is able to evolve the complete QuMLP architecture and parameters, as well as searches for the best time lags to optimally describe financial phenomena. In the attempt to improve the QuMLP parameters supplied by QIEA, each individual of the QIEA population is further trained by the complex back-propagation (CBP) algorithm. Also, for each forecasting model generated, we use a phase fix procedure to adjust time phase distortions that appear in financial time series. Furthermore, an experimental analysis is conducted with the proposed method through six real world financial time series, and the obtained results are discussed and compared to results found with the best methods recently presented in the literature.