PERBANDINGAN PERAMALAN HARGA SAHAM PT BANK CENTRAL ASIA TBK MENGGUNAKAN MODEL ARIMA DAN HIBRIDA TSR-ARIMA

Abstract

Stocks of PT Bank Central Asia Tbk. is one of the most desirable stocks for investors due to its high liquidity index. Different stock prices every day encourage investors to predict profits and losses that may occur. Forecasting becomes the solution to predict stock prices for the next few periods. Autoregressive Integrated Moving Average (ARIMA) and Time Series Regression (TSR) are models that can be used in forecasting time series data. This study aims to compare the accuracy of forecasting the stock price of PT Bank Central Asia Tbk. using the ARIMA and hybrid TSR-ARIMA models based on the MAPE value. The data used is daily stock price data on weekdays of PT Bank Central Asia Tbk. obtained from the Yahoo Finance with the period June 24, 2022 to June 13, 2023. The result shows that the best ARIMA model is ARIMA (1,1,0) with MAPE values of training and testing data are 0,9624% and 0,4632% respectively, while the best TSR-ARIMA model is TSR-ARIMA (1,1,0) with MAPE values of training and testing data are 0,9628% and 0,4467% respectively. Thus, TSR-ARIMA is the best model because it has a smaller MAPE value of testing data.