Analisis Algoritma LSTM dan SVR untuk Memprediksi Saham Perbankan di Pasar Indonesia

Dina Agustina, Devni Prima Sari

Abstract


Penelitian ini membahas analisis komparatif algoritma Long Short-Term Memory (LSTM) dan Support Vector Regression (SVR) untuk memprediksi harga saham dari empat bankdi Indonesia: Bank BCA (BBCA.JK), Bank BNI (BBNI.JK), Bank BRI (BBRI.JK), dan Bank Mandiri (BMRI.JK). Studi ini dikarenakan semakin pentingnya prediksi harga saham yang akurat di pasar saham Indonesia untuk pengambilan keputusan yang lebih baik di sektor perbankan. Metodologi yang digunakan melibatkan pelatihan model LSTM dan SVR dengan menggunakan data saham historis dan mengevaluasi kinerja prediksi dengan menggunakan Root Mean Square Error (RMSE). Tujuannya adalah untuk mengetahui algoritma mana yang memiliki akurasi prediktif yang lebih baik untuk saham perbankan di pasar Indonesia. Hasilnya menunjukkan perbedaan yang mencolok dalam nilai RMSE antara model LSTM dan SVR pada bank-bank yang dipilih. LSTM menghasilkan nilai RMSE sebesar 84.2712, 103.7936, 15.5974, dan 26.8980 untuk masing-masing bank, sementara SVR menunjukkan nilai RMSE yang lebih rendah, yaitu 4.9627, 5.4234, 5.4234, dan 2.5470. Hasil penelitian menunjukkan bahwa algoritma SVR lebih baik dibandingkan LSTM dalam memprediksi harga saham perbankan, serta menunjukkan potensi penerapannya di pasar saham Indonesia untuk meningkatkan proses pengambilan keputusan investasi.


Keywords


LSTM, MAPE, RMSE, SVR, saham perbankan

Full Text:

PDF

References


P. Jorion, Value at Risk: The New Benchmark Managing Financial, Third. McGraw-Hill, 2006.

M. Leo, S. Sharma, and K. Maddulety, “Machine learning in banking risk management: A literature review,” Risks, vol. 7, no. 1, Mar. 2019, doi: 10.3390/risks7010029.

M. Zheng, “Studying Stock Prediction in the Context of Machine Learning Exemplified by Analyzing SVM and LSTM Models,” 2024.

R. D. Edwards, John Magee, and WH Charles Bassetti., Technical analysis of stock trends. CRC press, 2018.

R. Fernandez Martinez, P. Jimbert, J. Ibarretxe, and M. Iturrondobeitia, “Use of support vector machines, neural networks and genetic algorithms to characterize rubber blends by means of the classification of the carbon black particles used as reinforcing agent,” Soft comput, vol. 23, no. 15, pp. 6115–6124, Aug. 2019, doi: 10.1007/s00500-018-3262-2.

Y. Ma, R. Han, and W. Wang, “Portfolio optimization with return prediction using deep learning and machine learning,” Expert Syst Appl, vol. 165, Mar. 2021, doi: 10.1016/j.eswa.2020.113973.

M. Liangyu and J. Dong, “Robust mean-risk portfolio optimization using machine learning-based trade-off parameter,” Appl Soft Comput, 2021.

B. Jyotirmayee and A. Kumar Pasayat, “Prediction based mean-value-at-risk portfolio optimization using machine learning regression algorithms for multi-national stock markets,” Eng Appl Artif Intell, 2023.

E. Ruiz, D. Ferreño, M. Cuartas, A. López, V. Arroyo, and F. Gutiérrez-Solana, “Machine learning algorithms for the prediction of the strength of steel rods: an example of data-driven manufacturing in steelmaking,” Int J Comput Integr Manuf, vol. 33, no. 9, pp. 880–894, Sep. 2020, doi: 10.1080/0951192X.2020.1803505.

S. Hamori, M. Kawai, T. Kume, Y. Murakami, and C. Watanabe, “Ensemble Learning or Deep Learning? Application to Default Risk Analysis,” Journal of Risk and Financial Management, vol. 11, no. 1, p. 12, Mar. 2018, doi: 10.3390/jrfm11010012.

J. Brownlee Disclaimer, “Deep Learning for Time Series Forecasting Predict the Future with MLPs, CNNs and LSTMs in Python Acknowledgements Copyright Deep Learning for Time Series Forecasting,” 2019.

Z. Hu, Y. Zhao, and M. Khushi, “A survey of forex and stock price prediction using deep learning,” Mar. 01, 2021, MDPI AG. doi: 10.3390/ASI4010009.

G. Li, W. Chen, D. Li, D. Wang, and S. Xu, “Comparative Study of Short-Term Forecasting Methods for Soybean Oil Futures Based on LSTM, SVR, ES and Wavelet Transformation,” in Journal of Physics: Conference Series, IOP Publishing Ltd, 2020. doi: 10.1088/1742-6596/1682/1/012007.

Q. Q. Abuein, M. Q. Shatnawi, E. Y. Aljawarneh, and A. Manasrah, “Time Series Forecasting Model for the Stock Market using LSTM and SVR,” International Journal of Advances in Soft Computing and its Applications, vol. 16, no. 1, pp. 169–185, 2024, doi: 10.15849/IJASCA.240330.10.

Y. Song, C. Cai, D. Ma, and C. Li, “Modelling and forecasting high-frequency data with jumps based on a hybrid nonparametric regression and LSTM model,” Expert Syst Appl, vol. 237, Mar. 2024, doi: 10.1016/j.eswa.2023.121527.

R. C. Staudemeyer and E. R. Morris, “Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks,” Sep. 2019, [Online]. Available: http://arxiv.org/abs/1909.09586

J. Brownlee Disclaimer, “Deep Learning for Time Series Forecasting Predict the Future with MLPs, CNNs and LSTMs in Python Acknowledgements Copyright Deep Learning for Time Series Forecasting,” 2019.

J. Wang, J. Zhang, and X. Wang, “Bilateral LSTM: A two-dimensional long short-term memory model with multiply memory units for short-term cycle time forecasting in re-entrant manufacturing systems,” IEEE Trans Industr Inform, vol. 14, no. 2, pp. 748–758, 2018, doi: 10.1109/TII.2017.2754641.

D. Rosadi, W. Andriyani, D. Arisanty, and D. Agustina, “Prediction of Forest Fire Occurrence in Peatlands using Machine Learning Approaches,” in 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2020, 2020. doi: 10.1109/ISRITI51436.2020.9315359.

A. Molino and S. Carlo, “Forecasting value at risk and conditional value at risk using option market data,” J Forecast, vol. 7, pp. 1190–1213, 2021.




DOI: https://doi.org/10.15548/jostech.v4i2.9886

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 JOSTECH Journal of Science and Technology

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