Hybrid ICEEMDAN–SVD–LSTM Model for Short-Term Stock Closing Price Forecasting: A Multi-Sector Evaluation on the Indonesia Stock Exchange
DOI:
https://doi.org/10.36456/jstat.vol19.no1.a11694Keywords:
ICEEMDAN, LSTM, Stock Price Forecasting, Singular Value Decomposition, Time SeriesAbstract
This study develops and evaluates a hybrid ICEEMDAN–SVD–LSTM model for forecasting the daily closing prices of BBRI, UNVR, and UNTR over an observation period of 15 years (September 2010–September 2025). The novelty lies in applying ICEEMDAN–SVD–LSTM to stock forecasting on the still underexplored Indonesia Stock Exchange, and in systematically comparing decomposition- and denoising-based models within one uniform framework across three sectors with different volatility profiles. ICEEMDAN was chosen because it yields a cleaner decomposition, with fewer spurious modes and less residual noise than EMD, EEMD, and CEEMDAN, while Hankel-matrix-based SVD denoising increases the signal-to-noise ratio of each component before the LSTM forecasting stage. The model's performance was compared with seven benchmarks: LSTM, EMD–LSTM, EEMD–LSTM, CEEMDAN–LSTM, ICEEMDAN–LSTM, EEMD–SVD–LSTM, and CEEMDAN–SVD–LSTM. In terms of RMSE, MAE, and MAPE, ICEEMDAN–SVD–LSTM produced the lowest errors for all three stocks, with RMSE values of 16.4605 (BBRI), 24.3086 (UNVR), and 70.8494 (UNTR), and lower MAE and MAPE than every benchmark. A Diebold–Mariano test confirmed that this advantage is statistically significant against all benchmark models. These results indicate that the proposed model is effective for short-term stock price forecasting and can serve as a decision-support tool for investors and analysts, while acknowledging market risk.
References
[1] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
[2] Z. Wu and N. E. Huang, “ENSEMBLE EMPIRICAL MODE DECOMPOSITION: A NOISE-ASSISTED DATA ANALYSIS METHOD,” Adv. Adapt. Data Anal., vol. 01, no. 01, pp. 1–41, Jan. 2009, doi: 10.1142/S1793536909000047.
[3] M. E. Torres, M. A. Colominas, G. Schlotthauer, and P. Flandrin, “A complete ensemble empirical mode decomposition with adaptive noise,” in 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic: IEEE, May 2011, pp. 4144–4147. doi: 10.1109/ICASSP.2011.5947265.
[4] M. A. Colominas, G. Schlotthauer, and M. E. Torres, “Improved complete ensemble EMD: A suitable tool for biomedical signal processing,” Biomed. Signal Process. Control, vol. 14, pp. 19–29, Nov. 2014, doi: 10.1016/j.bspc.2014.06.009.
[5] G. Kalaiarasan, B. Premjith, and N. Madhu Manjiparambil, “A Forecast-Driven Deep Learning Framework Using ICEEMDAN and PatchTST for Stock Prediction and Dynamic Portfolio Optimization,” IEEE Access, vol. 13, pp. 218099–218122, 2025, doi: 10.1109/ACCESS.2025.3648786.
[6] W. Hao, X. Sun, C. Wang, H. Chen, and L. Huang, “A hybrid EMD-LSTM model for non-stationary wave prediction in offshore China,” Ocean Eng., vol. 246, p. 110566, Feb. 2022, doi: 10.1016/j.oceaneng.2022.110566.
[7] S. Li, G. Tang, X. Chen, and T. Lin, “Stock Index Forecasting Using a Novel Integrated Model Based on CEEMDAN and TCN-GRU-CBAM,” IEEE Access, vol. 12, pp. 122524–122543, 2024, doi: 10.1109/ACCESS.2024.3452426.
[8] S. Poongadan and M. C. Lineesh, “Non-linear Time Series Prediction using Improved CEEMDAN, SVD and LSTM,” Neural Process. Lett., vol. 56, May 2024, doi: 10.1007/s11063-024-11622-z.
[9] “19 Juta Investor Pasar Modal dan 8 Juta Investor Saham Tercapai di Penutupan Bulan Inklusi Keuangan 2025,” suit-baze. Accessed: Jun. 23, 2026. [Online]. Available: https://www.idx.co.id/
[10] “PNM Investment Management.” Accessed: Jun. 23, 2026. [Online]. Available: https://www.pnmim.com/detailberita/jumlah-investor-pasar-modal-ri-tembus-18-juta-dan-didominasi-anak-muda
[11] databoks.katadata.co.id, “Deretan Sektor Saham yang Paling Disukai Anak Muda, Apa Saja? | Pusat Data Ekonomi dan Bisnis Indonesia | Databoks.” Accessed: Jun. 23, 2026. [Online]. Available: https://databoks.katadata.co.id/ekonomi-makro/statistik/dcc2789e87ea5d9/deretan-sektor-saham-yang-paling-disukai-anak-muda-apa-saja
[12] A. T. Haryono, R. Sarno, and K. R. Sungkono, “Stock price forecasting in Indonesia stock exchange using deep learning: a comparative study,” Int. J. Electr. Comput. Eng. IJECE, vol. 14, no. 1, p. 861, Feb. 2024, doi: 10.11591/ijece.v14i1.pp861-869.
[13] B. Y. Dwiandiyanta, R. Hartanto, and R. Ferdiana, “Optimization of Stock Predictions on Indonesia Stock Exchange: A New Hybrid Deep Learning Method,” Eng. Technol. Appl. Sci. Res., vol. 15, no. 1, pp. 19370–19379, Feb. 2025, doi: 10.48084/etasr.9363.
[14] D. Dickey and W. Fuller, “Distribution of the Estimators for Autoregressive Time Series With a Unit Root,” JASA J. Am. Stat. Assoc., vol. 74, Jun. 1979, doi: 10.2307/2286348.
[15] R. S. Tsay, Nonlinear time series analysis. Hoboken: John Wiley & Sons, 2019.
[16] H. Hassani, R. Mahmoudvand, and M. Zokaei, “Separability and window length in singular spectrum analysis,” Comptes Rendus Mathématique, vol. 349, no. 17–18, pp. 987–990, Aug. 2011, doi: 10.1016/j.crma.2011.07.012.
[17] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Jan. 30, 2017, arXiv: arXiv:1412.6980. doi: 10.48550/arXiv.1412.6980.
[18] R. J. Hyndman and A. B. Koehler, “Another look at measures of forecast accuracy,” Int. J. Forecast., vol. 22, no. 4, pp. 679–688, Oct. 2006, doi: 10.1016/j.ijforecast.2006.03.001.
