Comparative Performance of Statistical and LSTM Based Arbitrage in the Indonesian Stock Market

Yunita Yunita, Indwiarti Indwiarti, Deni Saepudin

Abstract


This study compares the performance of traditional statistical arbitrage and Long Short-Term Memory (LSTM)–based deep arbitrage strategies in generating returns and risk-adjusted performance in the Indonesian stock market. A quantitative approach is employed using long-only trading simulations on daily closing prices of blue-chip financial sector stocks listed on the Indonesia Stock Exchange from April 2015 to April 2025. Stock pairs are selected based on correlation and cointegration criteria, while spread volatility is modeled using a GARCH (1,1) framework. To ensure a genuine out-of-sample evaluation, the sample is divided into an in-sample period from April 2015 to August 2021 for model training and parameter optimization, and an out-of-sample period from September 2021 to April 2025 for performance assessment. Strategy performance is evaluated using portfolio return and Sharpe ratio. The empirical results show that both strategies are feasible in the Indonesian market; however, the LSTM-based deep arbitrage strategy significantly outperforms the traditional statistical arbitrage approach, achieving a higher out-of-sample portfolio return (735% versus 482%) and a superior Sharpe ratio (1.67 versus 0.69). These findings indicate that deep learning–based arbitrage can provide substantial improvements in both return and risk-adjusted performance under long-only trading constraints in an emerging market context.

Keywords


Statistical arbitrage; Cointegration; Deep arbitrage; LSTM; Indonesian stocks.

Full Text:

PDF

References


Y.-Y. Chen, W.-L. Chen, and S.-H. Huang, “Developing arbitrage strategy in high-frequency pairs trading with filterbank cnn algorithm,” in Proceedings - 2018 IEEE International Conference on Agents, ICA 2018, 2018, pp. 113–116. doi: 10.1109/AGENTS.2018.8459920.

Y. Saleh, M. Pradana, and B. R. Kartawinata, “Comparative Forecasting of Indonesian Blue-Chip Stocks Using ARIMA, ANN and LSTM Models,” in 2025 IEEE 16th Control and System Graduate Research Colloquium, ICSGRC 2025 - Conference Proceedings, 2025, pp. 239–244. doi: 10.1109/ICSGRC65918.2025.11159813.

Y. Zhao, S. Xu, and J. Ossowski, “Deep Learning Meets Statistical Arbitrage: An Application of Long Short-Term Memory Networks to Algorithmic Trading,” J. Financ. Data Sci., vol. 4, no. 4, pp. 133–150, 2022, doi: 10.3905/jfds.2022.1.103.

R. A. Andhika Viadinugroho and D. Rosadi, “Long Short-Term Memory Neural Network Model for Time Series Forecasting: Case Study of Forecasting IHSG during Covid-19 Outbreak,” in Journal of Physics: Conference Series, 2021, vol. 1863, no. 1. doi: 10.1088/1742-6596/1863/1/012016.

M. Diqi and I. W. Ordiyasa, “Enhancing Stock Price Prediction in the Indonesian Market: A Concave LSTM Approach with Runrelu,” J. Autom. Mob. Robot. Intell. Syst., vol. 18, no. 3, pp. 69–77, 2024, doi: 10.14313/jamris/3-2024/24.

A. Flori and D. Regoli, “Revealing Pairs-trading opportunities with long short-term memory networks,” Eur. J. Oper. Res., vol. 295, no. 2, pp. 772–791, 2021, doi: 10.1016/j.ejor.2021.03.009.

B. Zhan, S. Zhang, H. S. Du, and X. Yang, “Exploring Statistical Arbitrage Opportunities Using Machine Learning Strategy,” Comput. Econ., vol. 60, no. 3, pp. 861–882, 2022, doi: 10.1007/s10614-021-10169-8.

V. Chang, X. Man, Q. Xu, and C.-H. Hsu, “Pairs trading on different portfolios based on machine learning,” Expert Syst., vol. 38, no. 3, 2021, doi: 10.1111/exsy.12649.

D. Yoshikawa, “A new investment method for statistical arbitrage using eigendecomposition to generate stationarity,” in Proceedings - 2023 14th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2023, 2023, pp. 663–666. doi: 10.1109/IIAI-AAI59060.2023.00130.

K. Priya, P. Balaraman, and C. Sundar, “Machine Learning vs. Traditional Models: A Comparative Analysis of LSTM and ARIMA for Stock Prediction With Management Education Applications,” in Integrating AI and Machine Learning into Business and Management Education, SRM Institute of Science and Technology, India: IGI Global, 2025, pp. 215–246. doi: 10.4018/979-8-3373-2150-9.ch009.

H. Rad, R. K. Y. Low, and R. Faff, “The profitability of pairs trading strategies: distance, cointegration and copula methods,” Quant. Financ., vol. 16, no. 10, pp. 1541–1558, 2016, doi: 10.1080/14697688.2016.1164337.

G. Van Houdt, C. Mosquera, and G. Nápoles, “A review on the long short-term memory model,” Artif. Intell. Rev., vol. 53, no. 8, pp. 5929–5955, 2020, doi: 10.1007/s10462-020-09838-1.

B. Do and R. Faff, “Does simple pairs trading still work?,” Financ. Anal. J., vol. 66, no. 4, pp. 83–95, 2010, doi: 10.2469/faj.v66.n4.1.

E. Gatev, W. N. Goetzmann, and K. G. Rouwenhorst, “Pairs trading: Performance of a relative-value arbitrage rule,” Rev. Financ. Stud., vol. 19, no. 3, pp. 797–827, 2006, doi: 10.1093/rfs/hhj020.

R. Marti and A. Reimat, “Bitcoin and global stock portfolio: Dynamics across short and long-term horizons,” 2025, doi: https://doi.org/10.1016/j.frl.2025.108918.

H. Margaretha, P. M. Tauhalomoan, P. Widjaja, and F. V Ferdinand, “Predictive Analysis of Stock Prices Using ARIMA and Hybrid ARIMA-LSTM Models in the Indonesian Market,” in 22nd International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2025, 2025. doi: 10.1109/ECTI-CON64996.2025.11101223.

H. Yirong and L. Yi, “Forecasting conditional volatility based on hybrid GARCH-type models with long memory, regime switching, leverage effect and heavy-tail: Further evidence from equity market,” North Am. J. Econ. Financ., vol. 72, 2024, doi: 102148.

S. S. Wibisono, K. Leviana, T. S. Muliadiredja, H. Margaretha, F. V Ferdinand, and J. Utomo, “Stock Price Prediction on LQ45’s Banking Sector Using Long-Short-Term Memory and Convolutional Neural Network,” in Proceedings - 2024 2nd International Conference on Technology Innovation and Its Applications, ICTIIA 2024, 2024. doi: 10.1109/ICTIIA61827.2024.10761865.

A. M. Hudzaifa, V. V Yang, and D. Y. Faidah, “THE IMPACT OF THE PRESIDENTIAL ELECTION ON IDX COMPOSITE PREDICTIONS USING LONG SHORT TERM MEMORY,” Barekeng, vol. 18, no. 4, pp. 2397–2412, 2024, doi: 10.30598/barekengvol18iss4pp2397-2412.

A. Hidayat and A. Sihabuddin, “Evaluating the impact of multiple leading indicator in forecasting next day stock price with lstm,” J. Theor. Appl. Inf. Technol., vol. 99, no. 2, pp. 293–303, 2021, [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85101374902&partnerID=40&md5=5b62bae8d6f776af84d609721794969d

Marverick, “What the Sharpe Ratio Means for Investors,” 2025.

W. Jiang, “Applications of deep learning in stock market prediction: Recent progress,” Expert Syst. Appl., vol. 184, 2021, doi: 10.1016/j.eswa.2021.115537.

F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” in COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference, 2020, pp. 757–770. doi: 10.18653/v1/2020.coling-main.66.

A. A. Alalwan, N. P. Rana, Y. K. Dwivedi, and R. Algharabat, “Social media in marketing: A review and analysis of the existing literature,” Telemat. Informatics, vol. 34, no. 7, pp. 1177–1190, 2017, doi: 10.1016/j.tele.2017.05.008.

Muhammad Haris Diponegoro, Sri Suning Kusumawardani, and Indriana Hidayah, “Tinjauan Pustaka Sistematis: Implementasi Metode Deep Learning pada Prediksi Kinerja Murid,” J. Nas. Tek. Elektro dan Teknol. Inf., vol. 10, no. 2, pp. 131–138, 2021, doi: 10.22146/jnteti.v10i2.1417.

K. L. Tan, C. P. Lee, K. S. M. Anbananthen, and K. M. Lim, “RoBERTa-LSTM: A Hybrid Model for Sentiment Analysis With Transformer and Recurrent Neural Network,” IEEE Access, vol. 10, pp. 21517–21525, 2022, doi: 10.1109/ACCESS.2022.3152828.




DOI: http://dx.doi.org/10.30829/zero.v9i3.27373

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Publisher :
Department of Mathematics
Faculty of Science and Technology
Universitas Islam Negeri Sumatera Utara Medan
📱 WhatsApp:085270009767 (Admin Official)
SINTA 2 Google Scholar CrossRef Garuda DOAJ