Forecasting the IDX Composite Index Through the End of 2026 Using the XGBoost Algorithm
Keywords:
Classification Accuracy, Financial Forecasting, IDX Composite Index, Machine Learning, XGBoost.Abstract
This study examined the ability of Extreme Gradient Boosting (XGBoost) to predict the direction of the IDX Composite Index (IHSG) across 20-, 40-, and 60-trading-day horizons associated with October–December 2026. Daily IHSG observations and supporting financial indicators, including energy prices, the USD/IDR exchange rate, major United States equity indices, and the VIX, were obtained from Yahoo Finance for December 17, 2010, through October 5, 2026, covering 3,828 trading days. Predictor variables were constructed using 1-, 5-, and 20-day return ratios, and binary targets distinguished upward from downward index movements. XGBoost classifiers were implemented in Python using Google Colaboratory, with chronological training and testing partitions of 80% and 20%. Testing accuracies were 55.25%, 52.23%, and 50.13% across the respective horizons. All three forecasts indicated UP/BULLISH movements, with estimated probabilities of 52.86%, 65.47%, and 60.11%. Confusion matrices revealed frequent false-positive bullish classifications and limited detection of declining markets. Relative to retrospective majority-class baselines, performance was marginally better at 20 days, weaker at 40 days, and equivalent at 60 days. Forecast probabilities should not be interpreted as expected percentage changes in IHSG. These findings indicate conditional upward signals but insufficient classification reliability to establish an impending market recovery or support independent investment decisions.
Downloads
References
Al Ishaqi, A. M. (2026, July 1). Daftar 10 saham penopang dan penekan IHSG semester I/2026. Bisnis.com. https://market.bisnis.com/read/20260701/7/1984660/daftar-10-saham-penopang-dan-penekan-ihsg-semester-i2026/2
Anam, S., Shamsuddin, M. R., Kustiawan, E., Mahanani, D. M., & Yusuf, F. I. (2026). Grey wolf-optimized XGBoost regressor for stock index prediction with financial features. BAREKENG: Jurnal Ilmu Matematika dan Terapan, 20(3), 2131–2150. https://doi.org/10.30598/barekengvol20iss3pp2131-2150
Bao, W., Cao, Y., Yang, Y., Che, H., Huang, J., & Wen, S. (2025). Data-driven stock forecasting models based on neural networks: A review. Information Fusion, 113, 102616. https://doi.org/10.1016/j.inffus.2024.102616
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785
Daqiqil, I. (2021). Machine learning: Teori, studi kasus, dan implementasi menggunakan Python. UR Press.
Deng, S., Huang, X., Zhu, Y., Su, Z., Fu, Z., & Shimada, T. (2023). Stock index direction forecasting using an explainable eXtreme Gradient Boosting and investor sentiments. The North American Journal of Economics and Finance, 64, 101848. https://doi.org/10.1016/j.najef.2022.101848
Deni, D. R., & Amalita, N. (2026). Application of temporal fusion transformer for multivariate forecasting of Indonesian composite stock price index. Journal of Multidisciplinary Science: MIKAILALSYS, 4(3), 6481–6508. https://doi.org/10.58578/mikailalsys.v4i3.12032
Dezhkam, A., & Manzuri, M. T. (2023). Forecasting stock market for an efficient portfolio by combining XGBoost and Hilbert–Huang transform. Engineering Applications of Artificial Intelligence, 118, 105626. https://doi.org/10.1016/j.engappai.2022.105626
Din, R. U., Ahmed, S., Khan, S. H., Albanyan, A., Hoxha, J., & Alkhamees, B. (2025). A novel decision ensemble framework: Attention-customized BiLSTM and XGBoost for speculative stock price forecasting. PLOS ONE, 20(4), e0320089. https://doi.org/10.1371/journal.pone.0320089
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054
Gao, J. (2025). Application of XGBoost in the A-shares stock market forecasting. In Proceedings of the 2024 5th International Conference on Big Data Economy and Information Management (pp. 503–511). Association for Computing Machinery. https://doi.org/10.1145/3724154.3724237
Google. (n.d.). Google Colaboratory notebook [Notebook]. https://colab.research.google.com/drive/1ETWilEnIu_vE5cx_S8AGZ8NV8tWQ7P_U
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223–2273. https://doi.org/10.1093/rfs/hhaa009
Han, Y., Kim, J., & Enke, D. (2023). A machine learning trading system for the stock market based on N-period Min-Max labeling using XGBoost. Expert Systems with Applications, 211, 118581. https://doi.org/10.1016/j.eswa.2022.118581
IDXChannel. (2026, July 7). IHSG koreksi 34,74 persen sepanjang semester I-2026, OJK ungkap penyebabnya. RCTI+. https://www.rctiplus.com/news/detail/idxchannel/5422806/ihsg-koreksi-34-74-persen-sepanjang-semester-i-2026--ojk-ungkap-penyebabnya
Indra, Supian, S., Sukono, Riaman, Saputra, M. P. A., Azahra, A. S., & Pirdaus, D. I. (2025). Stock return prediction on the LQ45 market index in the Indonesia Stock Exchange using a machine learning algorithm based on technical indicators. Journal of Risk and Financial Management, 18(12), 714. https://doi.org/10.3390/jrfm18120714
Kho, D. C., Purnomo, H. D., & Hendry, H. (2025). Performance analysis of gradient boosting models variants in predicting the direction of stock closing prices on the Indonesia Stock Exchange. BAREKENG: Jurnal Ilmu Matematika dan Terapan, 19(2), 1393–1408. https://doi.org/10.30598/barekengvol19iss2pp1393-1408
Kumbure, M. M., Lohrmann, C., Luukka, P., & Porras, J. (2022). Machine learning techniques and data for stock market forecasting: A literature review. Expert Systems with Applications, 197, 116659. https://doi.org/10.1016/j.eswa.2022.116659
Lidyana, V. (2026). IHSG babak belur di akhir semester I 2026, OJK ungkap penyebabnya. IDN Times. https://www.idntimes.com/business/economy/ihsg-babak-belur-di-akhir-semester-i-2026-ojk-ungkap-penyebabnya-00-3m8tp-ztyn6y
Liu, J. (2024). Predicting Chinese stock market using XGBoost multi-objective optimization with optimal weighting. PeerJ Computer Science, 10, e1931. https://doi.org/10.7717/peerj-cs.1931
Mardianto, M. F. F., Valida, H., Putri, F. F., Fauzi, D. M., & Pusporani, E. (2026). Prediction of the Indonesia Composite Index (ICI) using the ARCH GARCH approach and the Fourier series. BAREKENG: Journal of Mathematics and Its Applications, 20(1), 271–286. https://doi.org/10.30598/barekengvol20iss1pp0271-0286
Mohapatra, S., Mukherjee, R., Roy, A., Sengupta, A., & Puniyani, A. (2022). Can ensemble machine learning methods predict stock returns for Indian banks using technical indicators? Journal of Risk and Financial Management, 15(8), 350. https://doi.org/10.3390/jrfm15080350
Nensi, A. I. E., Al Maida, M., Notodiputro, K. A., Angraini, Y., & Mualifah, L. N. A. (2025). Performance analysis of ARIMA, LSTM, and hybrid ARIMA-LSTM in forecasting the composite stock price index. CAUCHY: Jurnal Matematika Murni dan Aplikasi, 10(2), 588–604. https://doi.org/10.18860/cauchy.v10i2.33379
Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020). A systematic review of fundamental and technical analysis of stock market predictions. Artificial Intelligence Review, 53(4), 3007–3057. https://doi.org/10.1007/s10462-019-09754-z
Oukhouya, H., Kadiri, H., El Himdi, K., & Guerbaz, R. (2023). Forecasting international stock market trends: XGBoost, LSTM, LSTM-XGBoost, and backtesting XGBoost models. Statistics, Optimization & Information Computing, 12(1), 200–209. https://doi.org/10.19139/soic-2310-5070-1822
Pebrianti, D., Kurniawan, H., Bayuaji, L., & Rusdah, R. (2024). XGBoost hyper-parameter tuning using particle swarm optimization for stock price forecasting. Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, 9(4), 1179–1195. https://doi.org/10.26555/jiteki.v9i4.27712
Sonkavde, G., Dharrao, D. S., Bongale, A. M., Deokate, S. T., Doreswamy, D., & Bhat, S. K. (2023). Forecasting stock market prices using machine learning and deep learning models: A systematic review, performance analysis and discussion of implications. International Journal of Financial Studies, 11(3), 94. https://doi.org/10.3390/ijfs11030094
Sürek, R. E., & Lau, W.-Y. (2025). A refined methodological approach: Long-term stock market forecasting with XGBoost. Journal of Intelligent Systems, 34(1), 823–846. https://doi.org/10.1515/jisys-2025-0027
Tony, Ratchagit, M., & Hiryanto, L. (2025). Forecasting Indonesian banking stock prices using Prophet, XGBoost, and ridge regression: A comparative analysis. Jurnal Teknik Informatika, 6(4), 2890–2901. https://doi.org/10.52436/1.jutif.2025.6.4.4973
Ulyah, S. M., Susanti, R., Andreas, C., Rahmayanti, I. A., Rifada, M., Fitriyani, N. L., & Ana, E. (2024). A multivariate regression with time series error in forecasting Jakarta Composite Index and stock prices of banking industry in Indonesia by considering COVID-19 effect. International Journal of Technology, 15(6), 1839–1850. https://doi.org/10.14716/ijtech.v15i6.5469
Vuong, P. H., Dat, T. T., Mai, T. K., Uyen, P. H., & The Bao, P. (2022). Stock-price forecasting based on XGBoost and LSTM. Computer Systems Science and Engineering, 40(1), 237–246. https://doi.org/10.32604/csse.2022.017685
Whaley, R. E. (2000). The investor fear gauge. The Journal of Portfolio Management, 26(3), 12–17. https://doi.org/10.3905/jpm.2000.319728
Yahoo Finance. (2026). Historical market data: IHSG, S&P 500, NASDAQ, Nikkei, Hang Seng, STI, VIX, UST 10Y, USD/IDR, DXY, Brent, WTI, gold, and coal [Data set]. Retrieved October 5, 2026, from https://finance.yahoo.com
Yun, K. K., Yoon, S. W., & Won, D. (2021). Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process. Expert Systems with Applications, 186, 115716. https://doi.org/10.1016/j.eswa.2021.115716
