Market Forecasting: Comparative Analysis of ARIMA and LSTM on Indonesian Banks

The aim of this research is to see the predictability rate of future stocks price using ARIMA and LSTM. There are many algorithms that are already present in the machine learning community and some of them are proven to be practical and preferred to be used in technical stocks predictions. The algorithms that are currently used in machine learning and in conjunction with stocks prediction are K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF), Neural Networks (NN), Deep Neural Networks (DNN), and Artificial Neural Networks (ANN). Among the popular machine learning algorithms out there, two algorithms with a strong connection to time series are ARIMA and LSTM. In this research, we are doing a comparative analysis of ARIMA and LSTM models to see the possibility of forecasting stock prices in the future using time-series algorithm.