Portfolio Optimization by Considering Return Predictions Using the ARIMA Method on Jakarta Islamic Index Sharia Stocks

Salwa Cendikia Millantika

doi:10.46336/ijqrm.v6i2.1012

Portfolio Optimization by Considering Return Predictions Using the ARIMA Method on Jakarta Islamic Index Sharia Stocks

Salwa Cendikia Millantika

Abstract

In investment decision-making, accurate return projections are an important component in maximizing profits while minimizing risk. This study aims to construct an optimal stock portfolio in the Jakarta Islamic Index (JII) sharia stock sector by considering return predictions using the Autoregressive Integrated Moving Average (ARIMA) model. The ARIMA model is used to forecast future stock returns based on historical data. The prediction results are then utilized as input for expected returns in the Mean-Variance portfolio optimization model developed by Markowitz. This model considers the trade-off between expected return and risk (variance), with the goal of forming an optimal portfolio. The portfolio is evaluated to compare the performance of the prediction-based portfolio with the historical return-based portfolio. This study is expected to contribute to data-driven quantitative investment strategies and statistical predictions. The results of this study indicate that the ARIMA model is effective in predicting stock returns, which in turn improves the efficiency of portfolio construction. The prediction-based portfolio yields a higher average weekly return of 0.87% compared to 0.65% from the historical-based portfolio. Furthermore, the risk level, measured by standard deviation, is slightly lower in the prediction-based portfolio (1.46%) than in the historical one (1.50%). This leads to a significant improvement in the Sharpe ratio, rising from 0.43 to 0.60. These findings demonstrate that integrating ARIMA-based predictions into the portfolio optimization process enhances overall performance by increasing return per unit of risk. Therefore, the use of forecasting models such as ARIMA in portfolio selection provides a valuable tool for investors seeking to make more informed, data-driven investment decisions—particularly within the context of sharia-compliant equity markets such as the Jakarta Islamic Index.

Full Text:

PDF

References

Bessler, W., & Wolff, D. (2024). Portfolio Optimization with Sector Return Prediction Models. Journal of Risk and Financial Management, 17(6). https://doi.org/10.3390/jrfm17060254

Box, G. E. P., & Jenkins, G. M. (1976). Time Series Analysis: Forecasting and Control. Holden-Day.

Chen, Y. (2023). Application of ARIMA Model in Portfolio Optimization. Advances in Economics, Management and Political Sciences, 26(1), 227–236. https://doi.org/10.54254/2754-1169/26/20230575

Gubu, L., Cahyono, E., Arman, A., Budiman, H., & Djafar, M. K. (2024). Optimasi Portofolio Mean-Variance Dengan Analisis Klaster Fuzzy C-Means. Jurnal Gaussian, 12(4), 593–604. https://doi.org/10.14710/j.gauss.12.4.593-604

Mercurio, P. J., Wu, Y., & Xie, H. (2020). An entropy-based approach to portfolio optimization. Entropy, 22(3), 1–17. https://doi.org/10.3390/e22030332

Nur Fadhila, S., & Zuliana, S. U. (2023). Optimasi Portofolio Saham Menggunakan Model Markowitz Berdasarkan Prediksi Harga Saham. Kaunia: Integration and Interconnection Islam and Science Journal, 18(1), 35–40. https://doi.org/10.14421/kaunia.3948

Rahmi, A., & Helma. (2023). Portofolio Optimal Dengan Mempertimbangkan Prediksi Return Menggunakan Metode Support Vector Regression ( SVR ). 7(March), 23745–23753.

Saputra, M. R. (2023). Optimasi Portofolio Berbasis Prediksi Return Saham Menggunakan Hybrid XGBoost dan Improved Firefly Algorithm untuk Saham dalam Indeks LQ45. 10(3), 3505–3514.

Thomas, R. L. (1997). Modern Econometrics: An Introduction. Addison-Wesley.

Wei, W. W. S. (2006). Time Series Analysis: Univariate and Multivariate Methods (Edisi Kedua). Pearson Addison Wesley.

Wulan Sari, D., Goejantoro, R., & Wahyuningsih, S. (2016). Estimasi Parameter Model ARIMA untuk Peramalan Debit Air Sungai Menggunakan Least Square dan Goal Programming (Parameter Estimation of an ARIMA Model for River Flow Forecasting Using Least Square and Goal Programming). Jurnal EKSPONENSIAL, 7(2).

DOI: https://doi.org/10.46336/ijqrm.v6i2.1012