Sains Malaysiana 52(3)(2023): 993-1009

http://doi.org/10.17576/jsm-2023-5203-22

 

A Comparative Study of Deep Learning Algorithms in Univariate and Multivariate Forecasting of the Malaysian Stock Market

(Kajian Perbandingan Algoritma Pembelajaran Mendalam dalam Peramalan Univariat dan Multivariat Pasaran Saham Malaysia)

 

MOHD.RIDZUAN AB. KHALIL1 & AZURALIZA ABU BAKAR2,*

 

1Malaysian Administrative Modernisation and Management Planning Unit (MAMPU), Federal Government Administrative Centre, 62502 Putrajaya, Federal Territory, Malaysia

2Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia 43600 UKM Bangi, Selangor Darul Ehsan, Malaysia

 

Diserahkan: 8 Ogos 2022/Diterima: 28 Disember 2022

 

Abstract

As part of a financial institution, the stock market has been an essential factor in the growth and stability of the national economy. Investment in the stock market is risky because of its price complexity and unpredictable nature. Deep learning is an emerging approach in stock market prediction modeling that can learn the non-linearity and complexity of stock market data. To date, not much study on stock market prediction in Malaysia employs the deep learning prediction model, especially in handling univariate and multivariate data. This study aims to develop a univariate and multivariate stock market forecasting model using three deep learning algorithms and compare the performance of those models. The algorithm intends to predict the close price of the Malaysian stock market using the Axiata Group Berhad and Petronas Gas Berhad from Bursa Malaysia, listed in Kuala Lumpur Composite Index (KLCI) datasets. Three deep learning algorithms, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are used to develop the prediction model. The deep learning models achieved the highest accuracy and outperformed the baseline models in short and long-term forecasts. It also shows that LSTM possessed the best deep learning model for the Malaysian stock market, achieving the lowest prediction error among the other models. Deep learning demonstrates the ability to handle univariate and multivariate data in preserving important information, thus forecasting the stock market. This finding is relatively significant as deep learning works well with high-dimensional datasets.

 

Keywords: CNN; deep learning; LSTM; MLP; multivariate; stock forecasting; time series; univariate

 

Abstrak

Pasaran saham merupakan sebahagian daripada institusi kewangan yang menjadi faktor penting dalam pertumbuhan dan kestabilan sesebuah ekonomi negara. Pelaburan dalam pasaran saham adalah sangat berisiko disebabkan oleh perubahan harganya yang rumit dan sifatnya yang sukar untuk diramal. Pembelajaran mendalam adalah satu pendekatan baharu yang semakin menonjol dalam ramalan pasaran saham kerana ia mampu mempelajari data pasaran saham yang tidak linear dan rumit. Sehingga kini, tidak banyak kajian yang dilakukan mengenai ramalan pasaran saham di Malaysia menggunakan pendekatan pembelajaran mendalam khususnya yang melibatkan pendekatan data univariat dan multivariat. Penyelidikan ini dijalankan untuk membangunkan model ramalan pasaran saham univariat dan multivariat menggunakan tiga algoritma pembelajaran mendalam dan seterusnya membuat perbandingan prestasi antara model tersebut. Ia akan meramal harga tutup di pasaran saham Malaysia menggunakan data saham Axiata Group Berhad dan Petronas Gas Berhad dari Bursa Malaysia dan turut tersenarai di dalam Indeks Komposit Kuala Lumpur (KLCI). Tiga algoritma pembelajaran mendalam iaitu Multilayer Perceptron (MLP), Convolutional Neural Network (CNN) dan Long Short-Term Memory (LSTM) digunakan untuk membangunkan model ramalan. Hasil uji kaji menunjukkan model pembelajaran mendalam mencapai ketepatan yang tinggi dan mengatasi kesemua model dasar bagi ramalan untuk tempoh jangka pendek dan panjang. Ia juga menunjukkan LSTM merupakan model pembelajaran mendalam yang terbaik untuk pasaran saham Malaysia dengan ralat ramalan yang paling rendah berbanding kesemua model lain. Pembelajaran mendalam menunjukkan keupayaan yang ketara dalam membuat ramalan pasaran saham menggunakan data univariat dan multivariat. Penemuan ini adalah signifikan dengan keupayaan pembelajaran mendalam terutamanya dalam mempelajari set data yang bersifat multidimensi dan mempunyai fitur yang banyak.

 

Kata kunci: CNN; LSTM; MLP; pembelajaran dalam; multivariat; ramalan saham; siri masa; univariat

 

RUJUKAN

Abu-Mostafa, Y.S. & Atiya, A.F. 1996. Introduction to financial forecasting. Applied Intelligence 6(3): 205-213.

Al-Mashhadani, A.F.S., Hishan, S.S., Awang, H. & Alezabi, K.A.A. 2021. Forecasting Malaysian Stock Price using Artificial Neural Networks (ANN). Journal of Contemporary Issues in Business and Government 27(1): 4466-4482.

Azam, M., Haseeb, M., Samsi, A.B. & Raji, J.O. 2016. Stock market development and economic growth: Evidences from Asia-4 countries. International Journal of Economics and Financial Issues 6(3): 1200-1208.

Bustos, O. & Pomares-Quimbaya, A. 2020. Stock market movement forecast: A systematic review. Expert Systems with Applications 156: 113464.

Cao, J., Li, Z. & Li, J.  2019. Financial time series forecasting model based on CEEMDAN and LSTM. Physica A: Statistical Mechanics and Its Applications 519: 127-139.

Chung, H. & Shin, K.S. 2020. Genetic algorithm-optimized multi-channel convolutional neural network for stock market prediction. Neural Computing and Applications 32(12): 7897-7914.

Fister, D., Mun, J.C., Jagric, V. & Jagric, T. 2019. Deep learning for stock market trading: A superior trading strategy? Neural Network World 29(3): 151-171.

Gandhmal, D.P. & Kumar, K. 2019. Systematic analysis and review of stock market prediction techniques. Computer Science Review 34: 100190.

Hafizah Bahaludin & Saiful Hafizah Jaaman. 2013. Peta pasaran saham Malaysia. Journal of Quality Measurement and Analysis 9(2): 27-36.

He, K., Zhang, X., Ren, S. & Sun, J. 2016. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2016-December. pp. 770-778.

Hiransha, M., Gopalakrishnan, E.A., Menon, V.K. & Soman, K.P. 2018. NSE stock market prediction using deep-learning models. Procedia Computer Science 132(Iccids): 1351-1362.

Hoseinzade, E. & Haratizadeh, S.  2019. CNNpred: CNN-based stock market prediction using a diverse set of variables. Expert Systems with Applications 129: 273-285.

Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L. & Muller, P.A. 2019. Deep learning for time series classification: A review. Data Mining and Knowledge Discovery 33(4): 917-963.

Jiang, W. 2021. Applications of deep learning in stock market prediction: Recent progress. Expert Systems with Applications 184(March 2020): 115537.

Krizhevsky, B.A., Sutskever, I. & Hinton, G.E. 2012. ImageNet classification with deep convolutional neural networks. Communications of the ACM 60(6): 84-90.

Lee, M.C., Chang, J.W., Hung, J.C. & Chen, B.L. 2021. Exploring the effectiveness of deep neural networks with technical analysis applied to stock market prediction. Computer Science and Information Systems 18(2): 401-418.

Liu, H. & Song, B. 2018. Stock price trend prediction model based on deep residual network and stock price graph. Proceedings - 2018 11th International Symposium on Computational Intelligence and Design 2: 328-331.

Liu, H. & Long, Z. 2020. An improved deep learning model for predicting stock market price time series. Digital Signal Processing: A Review Journal 102: 102741.

Livieris, I.E., Pintelas, E. & Pintelas, P. 2020. A CNN–LSTM model for gold price time-series forecasting. Neural Computing and Applications 32(23): 17351-17360.

Maiti, A. & Shetty, D.P. 2020. Indian stock market prediction using deep learning. IEEE Region 10 Annual International Conference, Proceedings/TENCON 2020-Novem: pp. 1215-1220.

Masoud, N.M.H. 2013. The impact of stock market performance upon economic growth. International Journal of Economics and Financial Issues 3(4): 788-798.

Mehtab, S. & Sen, J. 2020. Stock Price Prediction Using Convolutional Neural Networks on a Multivariate Timeseries. https://doi.org/10.36227/techrxiv.15088734.v1

Mehtab, S., Sen, J. & Dasgupta, S. 2020. Robust analysis of stock price time series using CNN and LSTM-based deep learning models. Proceedings of the 4th International Conference on Electronics, Communication and Aerospace Technology. pp. 1481-1486.

Mehtab, S., Sen, J. & Dutta, A. 2021. Stock price prediction using machine learning and LSTM-based deep learning models. Communications in Computer and Information Science 1366: 88-106.

Nabipour, M., Nayyeri, P., Jabani, H., Mosavi, A., Salwana, E. & Shahab, S. 2020. Deep learning for stock market prediction. Entropy 22(8): 840.

Nikou, M., Mansourfar, G. & Bagherzadeh, J. 2019. Stock price prediction using DEEP learning algorithm and its comparison with machine learning algorithms. Intelligent Systems in Accounting, Finance and Management 26(4): 164-174.

Pak, M. & Kim, S. 2018. A review of deep learning in image recognition. Proceedings of the 2017 4th International Conference on Computer Applications and Information Processing Technology, CAIPT 2017 2018-Janua. pp. 1-3.

Pan, W., Li, J. & Li, X. 2020. Portfolio learning based on deep learning. Future Internet 12(11): 1-13.

Pradhan, R.P. 2018. Development of stock market and economic growth: The G-20 evidence. Eurasian Economic Review 8(2): 161-181.

Rama Krishna, V., Subhamastan Rao, T., Narayana, G.V.S. & Rachapudi, V. 2020. A model for stock price predictions using deep learning techniques. International Journal of Advanced Trends in Computer Science and Engineering 9(5): 8266-8271.

Selvin, S., Vinayakumar, R., Gopalakrishnan, E.A., Menon, V.K. & Soman, K.P. 2017. Stock price prediction using LSTM, RNN, and CNN-sliding window model. 2017 International Conference on Advances in Computing, Communications, and Informatics, ICACCI 2017 2017-Janua. pp. 1643-1647.

Sezer, O.B., Gudelek, M.U. & Ozbayoglu, A.M. 2020. Financial time series forecasting with deep learning: A systematic literature review: 2005-2019. Applied Soft Computing Journal 90: 106181.

Shen, J. & Shafiq, M.O. 2020. Short-term stock market price trend prediction using a comprehensive deep learning system. Journal of Big Data 7: Article No. 66.

Sismanoglu, G., Onde, M.A., Kocer, F. & Sahingoz, O.K. 2019. Deep learning based forecasting in stock market with big data analytics. 2019 Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science. pp. 1-4.

Soon, G.K., On, C.K., Rayner, A., Patricia, A. & Teo, J. 2018. A CIMB stock price prediction case study with feedforward neural network and recurrent neural network. Journal of Telecommunication, Electronic and Computer Engineering 10(3-2): 89-94.

Yiing, A.T.S. & Thim, C.K. 2015. Prediction of Bursa Malaysia Stock Index using autoregressive integrated moving average and artificial neural network. Malaysia Statistics Conference (MyStats 2015) 1997: 95.

Yong, B.X., Abdul Rahim, M.R. & Abdullah, A.S.  2017. A stock market trading system using deep neural network. Communications in Computer and Information Science 751: 356-364.

Zeroual, A., Harrou, F., Dairi, A. & Sun, Y. 2020. Deep learning methods for forecasting COVID-19 time-Series data: A comparative study. Chaos, Solitons and Fractals 140: 110121.

Zhao, Y. & Khushi, M. 2020. Wavelet Denoised-ResNet CNN and LightGBM method to predict forex rate of change. IEEE International Conference on Data Mining Workshops, ICDMW 2020-November. pp. 385-391.

Zulqarnain, M., Ghazali, R., Ghouse, M.G., Hassim, Y.M.M. & Javid, I. 2020. Predicting financial prices of stock market using recurrent convolutional neural networks. International Journal of Intelligent Systems and Applications 12(6): 21-32.

 

*Pengarang untuk surat-menyurat; email: azuraliza@ukm.edu.my

 

   

sebelumnya