Hybrid Evolutionary Quantum Inspired Method to Adjust Time Phase Distortions in Financial Time Series

摘要

This work presents a hybrid evolutionary quantum inspired method to adjust time phase distortions present in financial time series, overcoming the random walk dilemma for financial prediction. It is 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 describe the time series generator phenomenon. An experimental analysis is conducted with the proposed approach through two real world financial time series, and the obtained results are discussed and compared to; results found with classical models in literature.