Comparative Analysis of Hybrid ARIMA-LSTM against Statistical and Machine Learning Benchmarks for Commodity Stock

Muhammad Iszul Wilsa; Heru Purnomo Kurniawan; Rizki  Dewantara; Dinda Febrihastatiwi; Indri  Setiawati

doi:10.58602/jaiti.v4i2.260

Muhammad Iszul Wilsa ^{(Corresponding Author)} Universitas Islam Negeri Siber Syekh Nurjati Cirebon
Heru Purnomo Kurniawan Universitas Islam Negeri Siber Syekh Nurjati Cirebon
Rizki Dewantara Universitas Islam Negeri Siber Syekh Nurjati Cirebon
Dinda Febrihastatiwi Universitas PGRI Semarang
Indri Setiawati Universitas Islam Negeri Siber Syekh Nurjati Cirebon

DOI: https://doi.org/10.58602/jaiti.v4i2.260

Keywords: ARIMA-LSTM, Stock Prices, Commodities, Deep Learning, Forecasting

Abstract

Predicting stock prices in Indonesia’s commodities and energy sectors is a complex challenge due to high volatility influenced by global market dynamics and macroeconomic factors. This study aims to test the robustness of the ARIMA-LSTM hybrid model in predicting closing stock prices for six major issuers: ADRO, PTBA, MEDC, ANTM, MDKA, and AALI. The proposed approach employs a dual-input strategy that integrates 27 technical indicators with the linear residuals from the ARIMA model. The research methodology begins with data decomposition using the ARIMA model to capture linear components, followed by modeling the residuals using Long Short-Term Memory (LSTM) to capture complex non-linear patterns. The experimental results show that the hybrid model consistently delivers the best performance compared to single models such as ARIMA, Random Forest, and Single LSTM across all test datasets. In the 1-step-ahead scenario, the hybrid model achieved the lowest average MAPE of 2.20%, while in the 5-step-ahead scenario, the error rate remained at 3.98%. A key finding of this research is the hybrid architecture’s ability to mitigate the extreme overfitting experienced by the Single LSTM model, while providing better prediction stability against variations in issuer characteristics. This study concludes that the integration of statistical decomposition and deep learning provides a reliable framework for investors and analysts to make data-driven decisions amid the volatile fluctuations of the Indonesian capital market.

Downloads

Download data is not yet available.

References

H. Hamzah and S. Winardi, “Effective Stock Prediction Model Using MACD Method,” International Journal of Informatics and Computation, vol. 4, no. 2, p. 1, Dec. 2022, doi: 10.35842/ijicom.v4i2.51.

F. Rihaadatul Aisyi and O. Rohaeni, “Perbandingan Simple Linear Regressiondan Double Exponential Smoothing dalam Memprediksi Harga Saham,” Jurnal Riset Matematika, pp. 167–176, Dec. 2023, doi: 10.29313/jrm.v3i2.2836.

S. Latif, N. Javaid, F. Aslam, A. Aldegheishem, N. Alrajeh, and S. H. Bouk, “Enhanced prediction of stock markets using a novel deep learning model PLSTM-TAL in urbanized smart cities,” Heliyon, vol. 10, no. 6, p. e27747, Mar. 2024, doi: 10.1016/j.heliyon.2024.e27747.

Z. Shi, Z. Wu, S. Shi, C. Mao, Y. Wang, and L. Zhao, “High-Frequency Forecasting of Stock Volatility Based on Model Fusion and a Feature Reconstruction Neural Network,” Electronics (Basel)., vol. 11, no. 23, p. 4057, Dec. 2022, doi: 10.3390/electronics11234057.

E. Abnaina and F. Swandari, “Pengaruh Variabel Makroekonomi Dan Variabel Global Index Tehadap Indeks Harga Saham Gabungan (IHSG),” Jurnal Manajemen dan Bisnis Performa, vol. 19, no. 01, pp. 83–92, Mar. 2022, doi: 10.29313/performa.v19i01.9724.

A. Firnanda and B. Budiasih, “Performa Saham Sektor Energi selama Periode Covid-19 Delta dan Omicron di Indonesia,” Seminar Nasional Official Statistics, vol. 2023, no. 1, pp. 331–342, Oct. 2023, doi: 10.34123/semnasoffstat.v2023i1.1627.

N. P. G. Darmayanti and I. K. Yadnyana, “Does firm size can moderate the effect of dividend pay-out ratio and leverage on stock volatility?,” International journal of business, economics & management, vol. 6, no. 2, pp. 148–154, Jun. 2023, doi: 10.21744/ijbem.v6n2.2138.

R. K. Si, S. K. Padhan, and Dr. B. Bishi, “Application of Box – Jenkins ARIMA (p, d, q) Model for Stock Price Forecasting and Detect Trend of S&P BSE Stock Index: An Evidence from Bombay Stock Exchange,” Scholars Journal of Physics, Mathematics and Statistics, vol. 7, no. 7, pp. 110–125, Jul. 2020, doi: 10.36347/sjpms.2020.v07i07.006.

John Mark Limel Papag, Mary Grace Puma, and Gabriela Nichole Lim, “Forecasting the Daily Stock Prices of the Philippine Stock Exchange Index During the Opening and Closing of the Market,” International Journal For Multidisciplinary Research, vol. 5, no. 3, May 2023, doi: 10.36948/ijfmr.2023.v05i03.3246.

K. Gerakoudi, D. Georgoulas, and P. J. Stavroulakis, “A novel hybrid ARIMA-LSTM model for maritime shipping stock forecasting: comparative evidence against statistical and machine learning benchmarks,” Maritime Business Review, vol. 11, no. 1, pp. 2–20, Mar. 2026, doi: 10.1108/MABR-04-2024-0035.

N. Li, “Literature Review: Machine Learning in Stock Predictions,” Highlights in Business, Economics and Management, vol. 24, pp. 853–859, Jan. 2024, doi: 10.54097/81x6z947.

G. Sonkavde, D. S. Dharrao, A. M. Bongale, S. T. Deokate, D. Doreswamy, and S. K. Bhat, “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, vol. 11, no. 3, p. 94, Jul. 2023, doi: 10.3390/ijfs11030094.

J. Zhang, K. Cai, and J. Wen, “A survey of deep learning applications in cryptocurrency,” iScience, vol. 27, no. 1, p. 108509, Jan. 2024, doi: 10.1016/j.isci.2023.108509.

D. Xiao and J. Su, “Research on Stock Price Time Series Prediction Based on Deep Learning and Autoregressive Integrated Moving Average,” Sci. Program., vol. 2022, pp. 1–12, Mar. 2022, doi: 10.1155/2022/4758698.

S. A. Alokley, S. Araichi, and G. Alomair, “Exploring the Relationship and Predictive Accuracy for the Tadawul All Share Index, Oil Prices, and Bitcoin Using Copulas and Machine Learning,” Energies (Basel)., vol. 17, no. 13, p. 3241, Jul. 2024, doi: 10.3390/en17133241.

K. Li, “BILSTM Model for Machine Learning Stock Prediction and Portfolio Construction in the Context of Covid-19 Pandemic,” Finance & Economics, vol. 1, no. 8, Aug. 2024, doi: 10.61173/q8zeqe61.

A. Kulaglic and B. Berk Ustundag, “Stock Price Prediction Using Predictive Error Compensation Wavelet Neural Networks,” Computers, Materials & Continua, vol. 68, no. 3, pp. 3577–3593, 2021, doi: 10.32604/cmc.2021.014768.

P. Lv, Q. Wu, J. Xu, and Y. Shu, “Stock Index Prediction Based on Time Series Decomposition and Hybrid Model,” Entropy, vol. 24, no. 2, p. 146, Jan. 2022, doi: 10.3390/e24020146.

Z. D. Akşehir and E. Kılıç, “2LE-BO-DeepTrade: an integrated deep learning framework for stock price prediction,” PeerJ Comput. Sci., vol. 11, p. e3107, Aug. 2025, doi: 10.7717/peerj-cs.3107.

D. A. HSIEH, “Chaos and Nonlinear Dynamics: Application to Financial Markets,” J. Finance, vol. 46, no. 5, pp. 1839–1877, Dec. 1991, doi: 10.1111/j.1540-6261.1991.tb04646.x.

J. Liu, “Navigating the Financial Landscape: The Power and Limitations of the ARIMA Model,” Highlights in Science, Engineering and Technology, vol. 88, pp. 747–752, Mar. 2024, doi: 10.54097/9zf6kd91.

G. Kumar, U. P. Singh, and S. Jain, “An adaptive particle swarm optimization-based hybrid long short-term memory model for stock price time series forecasting,” Soft comput., vol. 26, no. 22, pp. 12115–12135, Nov. 2022, doi: 10.1007/s00500-022-07451-8.

K. Mahboob, M. H. Shahbaz, F. Ali1, and R. Qamar, “Predicting the Karachi Stock Price index with an Enhanced multi-layered Sequential Stacked Long-Short-Term Memory Model,” VFAST Transactions on Software Engineering, vol. 11, no. 2, pp. 249–255, Jun. 2023, doi: 10.21015/vtse.v11i2.1571.

A. M. Priyatno, L. S. Tanjung, W. F. Ramadhan, P. Cholidhazia, P. Z. Jati, and F. I. Firmananda, “Comparison Random Forest Regression and Linear Regression For Forecasting BBCA Stock Price,” Jurnal Teknik Industri Terintegrasi, vol. 6, no. 3, pp. 718–732, Jul. 2023, doi: 10.31004/jutin.v6i3.16933.