TY - JOUR AU - Putri Humairah AU - Dina Agustina PY - 2024/11/25 Y2 - 2025/04/03 TI - Stock Price Index Prediction Using Random Forest Algorithm for Optimal Portfolio JF - Jurnal Varian JA - Varian VL - 8 IS - 1 SE - Articles DO - https://doi.org/10.30812/varian.v8i1.4276 UR - https://journal.universitasbumigora.ac.id/index.php/Varian/article/view/4276 AB - With a majority Muslim population in Indonesia, Islamic capital markets such as the Jakarta IslamicIndex (JII) are a relevant choice because the JII is an investment index that complies with Sharia principles. This research aims to predict stock prices in the JII using the Random Forest (RF) algorithm andform an optimal portfolio with the Mean-Variance Efficient Portfolio (MVEP) model. The data used isthe daily closing price of JII stocks from April 2023 to March 2024, obtained from the Indonesia StockExchange and Yahoo Finance. The RF method is used to predict stock prices, with model performanceevaluation using Mean Absolute Percentage Error (MAPE). The results showed that the application ofML with the RF algorithm in predicting stock prices produced very good predictions because the evaluation results using MAPE were in the 0%-10% range, namely a value of 2.522% for ACES shares;1.222% for ICBP shares, and 0.760% for INDF shares. The optimal portfolio formed using MVEPproduces a stock composition with a weight of 7.64% for ACES, 22.46% for ICBP, and 69.90% forINDF. The optimal portfolio’s estimated expected return and risk are 0.0546% and 0.0103%. ER -