Algorithm Optimizer in GA-LSTM for Stock Price Forecasting

Abstract

The training and success of deep learning is strongly influenced by the selection of hyperparameters. This research uses a hybrid method between the genetic algorithm (GA) and long short-term memory (LSTM) to find a suitable model for predicting stock prices. GA is used to optimize the architecture, such as the number of epochs, window size, and LSTM units in the hidden layer. Tuning optimizer is also carried out using several optimizers to achieve the best value. The method that has been applied shows that the method has a good level of accuracy with mean absolute percentage error (MAPE) values below 10% in every optimizer used. A fairly stable and small value is generated by setting it using the Adam optimizer.