Integrating garch, markowitz mean–variance, and lstm for risk, volatility, and portfolio analysis of four major Indonesian banking stocks 2015 – 2024
Main Article Content
Abstract
This study examines the risk structure, volatility behavior, and optimal portfolio construction of four major banking stocks in Indonesia BBCA, BBRI, BMRI, and BBNI during the 2015–2024 period through the integration of the GARCH(1,1) model, Markowitz Mean–Variance optimization, and Long Short-Term Memory (LSTM)-based forecasting. Daily closing price data is transformed into log returns and tested for stationarity before further analysis. The GARCH estimation results indicate persistent high volatility across all stocks (?+? close to 1), with BBNI and BBRI the most responsive to market shocks, while BBCA remains the most stable stock. Markowitz optimization produces a Minimum Variance portfolio dominated by BBCA, while the Maximum Sharpe portfolio allocates funds entirely to BBCA due to its superior return efficiency. The LSTM is able to represent price trends well, as evidenced by low prediction error values for BBRI and BBNI and accuracy between 58–61 percent. The integration provides a comprehensive analytical framework for understanding changing market risk dynamics and supporting adaptive investment decision-making in the Indonesian banking sector. These findings confirm that the hybrid approach can improve risk mapping while maximizing portfolio performance through a combination of historical information, dynamic volatility, and price trend predictions.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
Ariefin, M. R. S., & Supangkat, S. H. (2024). Advanced stock price prediction in the Indonesian banking sector using sentiment analysis and CNN–LSTM models. Nanotechnology Perceptions, 20(7), 396–412. https://doi.org/10.62441/nano-ntp.v20i7.3854
Dharma, Y. D., Utami, A., & Pujiharta, P. (2025). Volatility forecasting using GARCH versus EGARCH models for cryptocurrencies, Indonesian stocks, and U.S. stocks. IJBE (Integrated Journal of Business and Economics), 9(2), 332-347. https://doi.org/10.33019/ijbe.v9i1.1125
Endri, E., Abidin, Z., Simanjuntak, T. P., & Nurhayati, I. (2020). Indonesian stock market volatility: GARCH model. Montenegrin Journal of Economics, 16(2), 7–17. https://doi.org/10.14254/1800-5845/2020.16-2.1
Kenrick, K., Ivancio, S. C., Isabellini, E., Adhi, C. G. S., & Prasetyo, A. (2024). Multivariate stock market forecasting using LSTM on Indonesian banking stock market. Procedia Computer Science, 245, 1047–1056. https://doi.org/10.1016/j.procs.2024.10.333
Khadafi, M., Ritonga, R. K., Ilham, M., & Putri, R. N. (2025). Analisis portofolio saham sektoral di BEI menggunakan model Markowitz: Studi kasus emiten LQ45 tahun 2021–2024. Jurnal Intelek dan Cendikiawan Nusantara, 2(3), 4235–4245.
Kinanti, S. L., & Rozana, I. (2025). Perbandingan performa model garch, lstm dan hybrid untuk prediksi harga saham syariah jii. RIGGS: Journal of Artificial Intelligence and Digital Business, 4(3), 7404-7411. https://doi.org/10.31004/riggs.v4i3.3109
Kurniansyah, J., Gusti, S. K., Yanto, F., & Affandes, M. (2025). Implementasi model Long Short-Term Memory (LSTM) dalam prediksi harga saham. Bulletin of Information Technology (BIT), 6(2), 79–86. https://doi.org/10.47065/bit.v5i2.1783
Maulana, Y. (2022). Pemodelan volatilitas indeks harga saham sektoral di Indonesia. Logika: Jurnal Penelitian Universitas Kuningan, 13(1), 53–72. https://doi.org/10.25134/logika.v13i01.5688
Nasution, M. A., & Al-khowarizmi, A. K. (2025). Data-driven portfolio optimization using k-means and markowitz model: evidence from LQ45 stocks. Economic: Journal Economic and Business, 4(2), 349-354. https://doi.org/10.56495/ejeb.v4i2.1155
Nismawati, N., Octavia, P. P., Khasanah, R. A., & Amalia, R. M. (2024). Optimalisasi portofolio saham dengan model Markowitz pada perusahaan manufaktur di Bursa Efek Indonesia periode Agustus 2023–Juli 2024. Lontara Journal of Mathematics, Statistics and Application, 1(1), 52–59. https://doi.org/10.61220/jmsa.v1i1.20241.512
Nurmawati, E., Abaysa, R., & Putra, R. A. (2025). Optimalisasi portofolio saham syariah berbasis prediksi menggunakan Long Short-Term Memory (LSTM). Jurnal Informatika: Jurnal Pengembangan IT, 10(2), 464–475. https://doi.org/10.30591/jpit.v10i2.8421
Pane, C. S. A., Fawwaz, A., Ryanti, M., & Khaddafi, M. (2025). Peran analisis portofolio dalam menentukan strategi investasi yang optimal. Jurnal Intelek dan Cendikiawan Nusantara, 2(3), 3989–3996.
Pulungan, A. F., & Lubis, R. S. (2025). Optimizing portfolio performance in Indonesian banking stocks: An empirical application of the Markowitz mean–variance framework. Desimal: Jurnal Matematika, 8(2), 237–246. https://doi.org/10.24042/nxebn152
Rafulta, E., Yanuar, F., Devianto, D., & Maiyastri. (2025). Pemodelan dan peramalan volatilitas memori panjang pada return saham ANTM: Studi komparatif model GARCH dan FIGARCH. Lattice Journal, 5(1), 75–89. http://dx.doi.org/10.30983/lattice.v5i1.9525
Raissa, Z. (2025). A comparative analysis of financial performance forecasting models: ARIMA, ARIMA-GARCH & LSTM in Indonesian banking stocks. Jurnal Ilmiah Manajemen Bisnis dan Inovasi, 12(1), 328–340. https://doi.org/10.35794/jmbi.v12i1.61515
Riski, T. R., & Sulistianingsih, H. (2024). Portofolio saham optimal dengan model Markowitz pada saham perbankan yang terdaftar di LQ45 tahun 2023. Jurnal Ekonomika dan Bisnis (JEBS), 4(4), 606–618. https://doi.org/10.47233/jebs.v4i4.1926
Sahid, I. H., & Budi, I. (2024). Leveraging LSTM predictions for enhanced portfolio allocation with Markowitz mean–variance optimization. The Indonesian Journal of Computer Science, 13(6), 9423–9432. https://doi.org/10.33022/ijcs.v13i6.4573
Saputra, M. P. A., Setyawan, D. P., & Wahid, A. J. (2025). Indonesian banking stock portfolio optimization based on Ridge Regression prediction. International Journal of Business, Economics and Social Development, 6(2), 330–337. https://doi.org/10.46336/ijbesd.v6i2.1064
Xu, K., Wu, Y., Jiang, M., Sun, W., & Yang, Z. (2024). Hybrid LSTM-GARCH framework for financial market volatility risk prediction. Journal of Computer Science and Software Applications, 4(5), 22-29. https://doi.org/10.5281/zenodo.13643010