Recurrent Neural Network With Gate Recurrent Unit For Stock Price Prediction

Abstract

Stock price prediction is a solution to reduce the risk of loss from investing in stocks go public. Although stock prices can be analyzed by stock experts, this analysis is analytical bias. Recurrent Neural Network (RNN) is a machine learning algorithm that can predict a time series data, non-linear data and non-stationary. However, RNNs have a vanishing gradient problem when dealing with long memory dependencies. The Gate Recurrent Unit (GRU) has the ability to handle long memory dependency data. In this study, researchers will evaluate the parameters of the RNN-GRU architecture that affect predictions with MAE, RMSE, DA, and MAPE as benchmarks. The architectural parameters tested are the number of units/neurons, hidden layers (Shallow and Stacked) and input data (Chartist and TA). The best number of units/neurons is not the same in all predicted cases. The best architecture of RNN-GRU is Stacked. The best input data is TA. Stock price predictions with RNN-GRU have different performance depending on how far the model predicts and the company's liquidity. The error value in this study (MAE, RMSE, MAPE) constantly increases as the label range increases. In this study, there are six data on stock prices with different companies. Liquid companies have a lower error value than non-liquid companies.