Adaptive Filter Design for Stock Market Prediction Using a Correlation-based Criterion

Abstract

This paper presents a novel adaptive-filter approach for predicting assets on the stock markets. Concepts are introduced here, which allow understanding this method and computing of the corresponding forecast. This approach is applied, as an example, through the prediction over the actual valuation of the PETR3 shares (Petrobras ON) traded in the Brazilian Stock Market. The first-rate choices of the window length and the number of filter coefficient are evaluated. This is done by observing the correlation between the predictor signal and the actual course performed by the market in terms of both the window prevision length and filter coefficient values. It is shown that such adaptive predictors furnish, on the average, very substantial profit on the invested amount.