Analisis Peramalan Harga Saham Menggunakan Metode ARIMA pada PT Astra Agro Lestari Tbk (AALI)

Stock Price Forecasting Analysis Using the ARIMA Method at PT Astra Agro Lestari Tbk (AALI)

Abstract

Penelitian ini bertujuan menganalisis dan memprediksi pergerakan harga saham PT Astra Agro Lestari Tbk (AALI) menggunakan metode Autoregressive Integrated Moving Average (ARIMA). Pergerakan harga saham AALI dipengaruhi oleh berbagai faktor, seperti kondisi ekonomi, harga Crude Palm Oil (CPO), inflasi, nilai tukar rupiah, dan dinamika pasar global, sehingga diperlukan metode peramalan yang akurat untuk mendukung pengambilan keputusan investasi. Data yang digunakan berupa harga penutupan saham yang diperoleh dari Bursa Efek Indonesia dan sumber keuangan lainnya. Tahapan penelitian meliputi pengumpulan data, pengujian stasioneritas, proses differencing, identifikasi model, estimasi parameter, evaluasi model, dan peramalan. Pemilihan model terbaik dilakukan berdasarkan indikator statistik seperti Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), dan Akaike Information Criterion (AIC). Hasil penelitian menunjukkan bahwa metode ARIMA mampu menghasilkan prediksi harga saham dengan tingkat akurasi yang baik serta menggambarkan pola pergerakan saham berdasarkan data historis. Temuan ini dapat dimanfaatkan investor dan perusahaan dalam menyusun strategi investasi serta pengambilan keputusan keuangan.

ABSTRACT

This study aims to analyze and predict the price movements of PT Astra Agro Lestari Tbk (AALI) shares using the Autoregressive Integrated Moving Average (ARIMA) method. AALI’s stock price movements are influenced by various factors, such as economic conditions, Crude Palm Oil (CPO) prices, inflation, the rupiah exchange rate, and global market dynamics; therefore, an accurate forecasting method is needed to support investment decision-making. The data used consists of closing stock prices obtained from the Indonesia Stock Exchange and other financial sources. The research stages include data collection, stationarity testing, differencing, model identification, parameter estimation, model evaluation, and forecasting. The best model was selected based on statistical indicators such as Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and the Akaike Information Criterion (AIC). The results of the study indicate that the ARIMA method is capable of producing stock price forecasts with a high degree of accuracy and of describing stock movement patterns based on historical data. These findings can be utilized by investors and companies in formulating investment strategies and making financial decisions.