Long Short-Term Memory Neural Network Model for Time Series Forecasting: Case Study of Forecasting IHSG during Covid-19 Outbreak

Abstract Long Short-Term Memory (LSTM) is one of the developments from Recurrent Neural Network (RNN) architecture. In this paper, we use LSTM architecture for modeling and forecasting Indonesian Composite Stock Price Index (IHSG) closing value data. We also compare performance method with ARIMA Radial Basis Function (RBF) method. implementation, both R Python open source software. For empirical study data January until August 2020 to see considered methods during Covid-19 pandemic periods time. From analysis, found that performs better than ARIMA, but outperformed by RBF