Combining An Lstm Neural Network With The Variance Ratio Test For Time Series Prediction And Operation On The Brazilian Stock Market

Forecasting financial time series is a problem studied by researchers from different fields, who are looking for effective ways to achieve financial gains. Over time, many authors conducted studies on the possible predictability of the series through different statistical tests, and recently several papers explore the application of machine learning algorithms to have better predictions. In this paper we analyzed real data of 11 time series related to Brazilian stocks, focusing on the statistical characteristics of the series and the use of an LSTM neural network to classify future values. We analyzed the results of 5 different variance ratio tests and their relationship with the neural network classification performance. This paper proposes the application of statistical tests in the LSTM training set to highlight previously those series that have more temporal dependence and, therefore, possibly better forecast results. The results showed that 5 out of 11 stocks rejected the random walk hypothesis through the variance ratio tests and that these same stocks obtained the best performances in terms of classification and financial return.