Asmiranda
Fakultas Ekonomi & Bisnis, Universitas Cenderawasih

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Penerapan Model ARIMA dalam Peramalan Harga Saham PT Samator Indo Gas, Tbk Herlina Tiku Datu; Jihan Ramadhani Syafri; Asmiranda; Jein Arung Tasik; Radian Januari Situmeang
Jurnal Penelitian Ekonomi Akuntansi Vol 10 No 1 (2026)
Publisher : Program Studi Akuntansi Fakultas Ekonomi Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33059/jensi.v10i1.14611

Abstract

This study aims to analyze and predict the daily closing price of PT Samator Indo Gas Tbk shares using the Autoregressive Integrated Moving Average (ARIMA) model based on three years of historical data. The research data consists of 775 daily stock price observations from January 1, 2023, to April 30, 2026, obtained from the website www.investing.com. Data preparation was performed using RStudio software. The analysis process included descriptive analysis, the Augmented Dickey-Fuller (ADF) stationarity test, model identification via Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) plots, ARIMA model specification, residual diagnostics, and model accuracy assessment. The research results indicate that the data is not stationary at the level but becomes stationary after first-order differencing. The best model obtained is ARIMA(2,1,1) with an AIC value of 8,536.785. The Ljung-Box test results show that the residuals exhibit white noise, making the model suitable for forecasting. The forecasting results over 20 periods indicate that AGII stock prices tend to move stably with a MAPE value of 1.71%. Thus, the ARIMA model is capable of being used for short-term forecasting of AGII stock prices. This study still has limitations because the modeling was performed using ARIMA, which relies on historical AGII stock price data without accommodating external variables that could potentially influence stock price movements. Therefore, future research could integrate macroeconomic factors and evaluate the performance of alternative methods, such as ARIMAX, GARCH, or LSTM, thereby improving the model’s ability to generate accurate forecasts.