Forecasting theStockPrice of PT Astra InternationalUsing theLSTM Method

Forecasting theStockPrice of PT Astra InternationalUsing theLSTM Method

forecasting; stock price; recurrent neural network; long short-term memor

Stocks are one of the long-term investment options and represent ownership in a company that can be acquired through buying and selling. Investment carries both profit potential and risks that must be faced by investors when they provide their capital to companies. Accurate stock price forecasts are very important because they provide an estimate of risk. This research aims to forecast the stock price of PT Astra International Tbk (ASII.JK) using a Long Short-TermMemory (LSTM) method. Datasetclosing stockprices weretaken from January 2,2015,to December 30,2020,with atotal observationof1506.This data setis dividedinto 80% for training and 20% for training.Theforecasting resultsshow that the best performance has MSE, MSE, MAE, and MAPE are 151.910, 23076.561, 118.128, and 2.3%, respectively. The model has a batch size of 4 and epochs of 50. This research recommends thatother partiesconsider this method when theyneed tomanage their investment risk in stocks

Edwin Setiawan Nugraha2, Zalfani Alika2, Dadang Amir Hamzah3

https://jurnal.iaii.or.id/index.php/RESTI/article/view/5699/944

Departmentof Actuarial Science, Facultyof Business, President University, Bekasi, Indonesia

28-06-2024

FAJAR BAGUS

PDF

ENGLISH

TEXT