A Comparative Analysis of LSTM, ARIMA, and MCMC Models for  Forecasting Financial Market

Deepika  Kirti

doi:10.48165/dbitdjr.2024.1.02.04

Authors

Deepika Kirti (Ph.D. Scholar, Department of Computer Science & Engineering, Delhi Skill and Entrepreneurship University) Author https://orcid.org/0000-0002-5314-0192

DOI:

https://doi.org/10.48165/dbitdjr.2024.1.02.04

Keywords:

ARIMA, LSTM, MCMC, Bayesian Model, Stock prediction, Stock market

Abstract

Machine learning, with its sophisticated predictive capabilities, has fundamentally transformed numerous fields, including stock trading. This research presents a comparative study of Bayesian inference using the Markov Chain Monte Carlo (MCMC) method in stock price prediction, the new paradigm of long short-term memory (LSTM) networks, and conventional auto-regressive integrated moving average (ARIMA) models. The study uses historical stock price data from a diverse array of companies to evaluate these models concerning their accuracy, robustness, and computational efficiency. The findings contribute to the ongoing discourse on effective forecasting methodologies in financial markets, offering valuable insights to stakeholders, practitioners, and researchers. These insights are particularly pertinent for navigating financial environments’ inherently unpredictable and dynamic nature.

References

Tanner, M. and Wong, W. (1987). “The calculation of posterior distributions by data augmentation.” J. American Statist. Assoc., 82: 528–550.

Chib, S., & Greenberg, E. (1995). Understanding the Metropolis Hastings Algorithm. The American Statistician, 49(4), 327– 335. https://doi.org/10.1080/00031305.1995.10476177

JHEE W, SHAW M. Neural Networks in Finance and Investing. Revised Edition, Irwin, Chicago. 1996.

Meyler, A., Kenny, G., & Quinn, T. (1998). Forecasting Irish inflation using ARIMA models.

Roberts GO, Rosenthal JS. Markov chain monte carlo. Encyclopedia of the Actuarial Sciences. 2003.

Tse YK, Zhang X, Yu J. Estimation of hyperbolic diffusion using the Markov chainMonte Carlo method. Quantitative Finance. 2003 Dec 3;4(2):158.

Robert, C. P., & Casella, G. (2004). Monte Carlo Statistical methods. In Springer texts in statistics. https://doi.org/10.1007/978-1- 4757-4145-2

McNelis PD. Neural networks in finance: gaining predictive edge in the market. Elsevier; 2005 Jan 20.

Pai, P. F., & Lin, C. S. (2005). A hybrid ARIMA and support vector machines model in stock price forecasting. Omega, 33(6), 497-505.

Shahwan T. Forecasting commodity prices using artificial neural networks. Mensch-und-Buch- Verlag; 2006.

Merh, N., Saxena, V. P., & Pardasani, K. R. (2010). A comparison between hybrid approaches of ANN and ARIMA for Indian stock trend forecasting. Business Intelligence Journal, 3(2), 23-43.

Graves A, Graves A. Long short-term memory. Supervised sequence labelling with recurrent neural networks. 2012:37-45. Akandwanaho, S. M., Adewumi, A. O., & Adebiyi, A. A. (2014). Solving dynamic traveling salesman problem using dynamic Gaussian process regression. Journal of Applied Mathematics, 2014(1), 818529.

Dai, A. M. (2015). Document embedding with paragraph vectors. arXiv preprint arXiv:1507.07998.

Selvin, S., Vinayakumar, R., Gopalakrishnan, E. A., Menon, V. K., & Soman, K. P. (2017, September). Stock price prediction using LSTM, RNN and CNN-sliding window model. In 2017 international conference on advances in computing, communications and informatics (icacci) (pp. 1643-1647). IEEE.

Siami-Namini, S., Tavakoli, N., & Namin, A. S. (2018, December). A comparison of ARIMA and LSTM in forecasting time series. In 2018 17th IEEE international conference on machine learning and applications (ICMLA) (pp. 1394-1401). Ieee.

Talagala TS, Hyndman RJ, Athanasopoulos G. Meta-learning how to forecast time series. Monash Econometrics and Business Statistics Working Papers. 2018 May;6(18):16.

Staudemeyer, R. C., & Morris, E. R. (2019). Understanding LSTM--a tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586.

Moghar, A., & Hamiche, M. (2020). Stock market prediction using LSTM recurrent neural network. Procedia computer science, 170, 1168-1173.

Xiao, R., Feng, Y., Yan, L., & Ma, Y. (2022). Predict stock prices with ARIMA and LSTM. arXiv preprint arXiv:2209.02407. Verma, S., Prakash Sahu, S., & Prasad Sahu, T. (2022, March). Ensemble approach for stock market forecasting using ARIMA and LSTM model. In Proceedings of Third International Conference on Intelligent Computing, Information and Control Systems: ICICCS 2021 (pp. 65-80). Singapore: Springer Nature Singapore.

Varaprasad, B. N., Kanth, C. K., Jeevan, G., & Chakravarti, Y. K. (2022, March). Stock Price Prediction using Machine Learning. In 2022 International Conference on Electronics and Renewable Systems (ICEARS) (pp. 1309-1313). IEEE.

Kobiela, D., Krefta, D., Król, W., & Weichbroth, P. (2022). ARIMA vs LSTM on NASDAQ stock exchange data. Procedia Computer Science, 207, 3836-384

Hamiane, S., Ghanou, Y., Khalifi, H., & Telmem, M. (2024). Comparative analysis of LSTM, ARIMA, and hybrid models for forecasting future GDP. Journal homepage: http://iieta. org/journals/isi, 29(3), 853-861.

Bi, C., & Wang, Y. (2024, August). Long Short Term Memory Network (LSTM) Model Based on Neural Networks in Financial Forecasting. In 2024 Second International Conference on Networks, Multimedia and Information Technology (NMITCON) (pp. 1-5). IEEE.

Nandam, M. D., & Reddy,M. B. S. (2024). Detection of intrusions using transformer-LSTM model. Interantional Journal of Scientific Research in Engineering and Management, 8(008).

Xu, J. (2024). Technology Company Stock Trend Prediction Based on ARIMA Model. Advances in Economics, Management and Political Sciences, 94, 240-247.

Liang, K., Wu, H., & Zhao, Y. (2024). Study of effectiveness of the ARIMA method in forecasting stock process in China. Theoretical and Natural Science, 43, 33-44