Approach With Bilstm: The Case of Forecasting Stock Closing Price
Abstract
— Peramalan saham merupakan salah satu tugas penting di pasar saham karena prediksi harga saham di masa depan dapat membantu investor dalam mengambil keputusan yang lebih baik. Penelitian ini mengkaji potensi jaringan Bidirectional Long Short-Term Memory (BiLSTM) sebagai bagian dari model deep learning untuk meningkatkan akurasi prediksi saham. Model BiLSTM yang diusulkan memanfaatkan kemampuan arsitektur model ini untuk menangkap ketergantungan jangka pendek dan jangka panjang dengan memproses data secara dua arah. Hal ini memungkinkan model untuk memanfaatkan informasi dari masa lalu dan masa depan secara simultan, memberikan prediksi yang lebih akurat. Model BiLSTM ini dievaluasi menggunakan metrik evaluasi seperti Mean Absolute Error (MAE), Root Mean Square Error (RMSE), dan Mean Absolute Percentage Error (MAPE). Penelitian ini menguji model pada beberapa saham, termasuk Apple, Gold, Oil, dan Silver. Hasil penelitian menunjukkan bahwa pendekatan BiLSTM tidak hanya efektif dalam memajukan metode peramalan harga penutupan saham, tetapi juga memiliki aplikasi praktis pada berbagai instrumen keuangan lainnya. Temuan ini memberikan kontribusi signifikan dalam bidang peramalan pasar saham, memperlihatkan bahwa BiLSTM dapat menjadi alat yang andal dan efektif dalam memprediksi pergerakan harga saham dan instrumen keuangan lainnya.
Kata kunci — peramalan saham, deep learning, BiLSTM.
References
M. Vijh, D. Chandola, V. A. Tikkiwal, and A. Kumar, "Stock Closing Price Prediction using Machine Learning Techniques," Procedia Comput. Sci., vol. 167, no. 2019, pp. 599–606, 2020, doi: 10.1016/j.procs.2020.03.326.
W. Jiang, "Applications of deep learning in stock market prediction: Recent progress," Expert Syst. Appl., vol. 184, no. March 2020, p. 115537, 2021, doi: 10.1016/j.eswa.2021.115537.
N. M. H. Masoud, "The impact of stock market performance upon economic growth," Int. J. Econ. Financ. Issues, vol. 3, no. 4, pp. 788–798, 2013.
C. Chikwira and J. I. Mohammed, "The Impact of the Stock Market on Liquidity and Economic Growth: Evidence of Volatile Market," Economies, vol. 11, no. 6, 2023, doi: 10.3390/economies11060155.
W. Khan, M. A. Ghazanfar, M. A. Azam, A. Karami, K. H. Alyoubi, and A. S. Alfakeeh, "Stock market prediction using machine learning classifiers and social media, news," J. Ambient Intell. Humaniz. Comput., vol. 13, no. 7, pp. 3433–3456, 2022, doi: 10.1007/s12652-020-01839-w.
X. Tang, N. Lei, M. Dong, and D. Ma, "Stock Price Prediction Based on Natural Language Processing1," Complexity, vol. 2022, 2022, doi: 10.1155/2022/9031900.
J. Guo and B. Tuckfield, "News-based Machine Learning and Deep Learning Methods for Stock Prediction," J. Phys. Conf. Ser., vol. 1642, no. 1, pp. 0–7, 2020, doi: 10.1088/1742-6596/1642/1/012014.
T. T. Teoh et al., "From Technical Analysis to Text Analytics: Stock and Index Prediction with GRU," Proc. IEEE 2019 9th Int. Conf. Cybern. Intell. Syst. Robot. Autom. Mechatronics, CIS RAM 2019, pp. 496–500, 2019, doi: 10.1109/CIS-RAM47153.2019.9095772.
H. N. Bhandari, B. Rimal, N. R. Pokhrel, R. Rimal, K. R. Dahal, and R. K. C. Khatri, "Predicting stock market index using LSTM," Mach. Learn. with Appl., vol. 9, no. May, p. 100320, 2022, doi: 10.1016/j.mlwa.2022.100320.
M. A. Istiake Sunny, M. M. S. Maswood, and A. G. Alharbi, "Deep Learning-Based Stock Price Prediction Using LSTM and Bi-Directional LSTM Model," 2nd Nov. Intell. Lead. Emerg. Sci. Conf. NILES 2020, pp. 87–92, 2020, doi: 10.1109/NILES50944.2020.9257950.
L. Xu, W. Xu, Q. Cui, M. Li, B. Luo, and Y. Tang, "Deep Heuristic Evolutionary Regression Model Based on the Fusion of BiGRU and BiLSTM," Cognit. Comput., pp. 1672–1686, 2023, doi: 10.1007/s12559-023-10135-6.
K. H. Lee and G. S. Jo, "Expert system for predicting stock market timing using a candlestick chart," vol. 16, pp. 357–364, 1999.
S. Siami-Namini, N. Tavakoli, and A. S. Namin, "The Performance of LSTM and BiLSTM in Forecasting Time Series," Proc. - 2019 IEEE Int. Conf. Big Data, Big Data 2019, pp. 3285–3292, 2019, doi: 10.1109/BigData47090.2019.9005997.
M. Rahimzad, A. Moghaddam, and N. Hosam, "Performance Comparison of an LSTM ‑ based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting," Water Resour. Manag., pp. 4167–4187, 2021, doi: 10.1007/s11269-021- 02937-w.
W. Lu, "A CNN-BiLSTM-AM method for stock price prediction," Neural Comput. Appl., vol. 33, no. 10, pp. 4741–4753, 2021, doi: 10.1007/s00521-020-05532-z.
T. Cho, U. Sunarya, M. Yeo, B. Hwang, and Y. S. Koo, "Deep-ACTINet : End-to-End Deep Learning Architecture for Automatic Sleep-Wake Detection Using Wrist Actigraphy", doi: 10.3390/electronics8121461.
J. Kim and N. Moon, "BiLSTM model based on multivariate time series data in multiple field for forecasting trading area," J. Ambient Intell. Humaniz. Comput., no. 0123456789, 2019, doi: 10.1007/s12652-019-01398-9. [18] S. Zaheer et al., "A Multi Parameter Forecasting for Stock Time Series Data Using LSTM and Deep Learning Model," Mathematics, vol. 11, no. 3, pp. 1–24, 2023, doi: 10.3390/math11030590. [19] Z. Zou and Z. Qu, "Using LSTM in Stock prediction and Quantitative Trading," CS230 Deep Learn., 2020. [20] C. Y. Lai, R. C. Chen, and R. E. Caraka, "Prediction Stock Price Based on Different Index Factors Using LSTM," Proc. - Int. Conf. Mach. Learn. Cybern., vol. 2019-July, pp. 1–6, 2019, doi: 10.1109/ICMLC48188.2019.8949162. [21] D. Singh and B. Singh, "Investigating the impact of data normalization on classification performance," Appl. Soft Comput., vol. 97, p. 105524, 2020. [22] Y. Liu, Y. Zhou, S. Wen, and C. Tang, "A Strategy on Selecting Performance Metrics for Classifier Evaluation," Int. J. Mob. Comput. Multimed. Commun., vol. 6, no. 4, pp. 20–35, 2014, doi: 10.4018/IJMCMC.2014100102.
