Modeling of the Microsoft Stock Prices Using Machine Learning and Classical Models: Identification of Optimal Model for Application


  • Chrysogonus Chinagorom Nwaigwe Department of Statistics, Federal University of Technology Owerri, Imo State, Nigeria
  • Desmond Chekwube Bartholomew Department of Statistics, Federal University of Technology Owerri, Imo State, Nigeria
  • Emmanuel Chigozie Umeh Department of Statistics, Federal University of Technology Owerri, Imo State, Nigeria
  • Godwin Onyeka Nwafor Department of Statistics, Federal University of Technology Owerri, Imo State, Nigeria
  • Ibrahim Adamu Department of Statistics, Federal University of Technology Owerri, Imo State, Nigeria
  • Simplicius Chidiebere Oguguo Department of Mathematics, Imo State College of Education, Ihitte Uboma, Imo State, Nigeria


Machine learning models, Traditional time series models, Stock prices, Support zone, Resistance zone


In this study, Microsoft stock price was modeled using two traditional time series models and two machine learning models for reliable predictions of the future behavior of the stock prices and more gainful investment. Model metrics such as AIC, BIC, Log-likelihood, RMSE, and confidence set test were the basis for comparison of the models. The results showed that the GARCH model outperformed the ARIMA and Support Vector Regression models while the Long Short-Time Memory –Recurrent model outperformed the GARCH model.  Forecasts from the Long Short-Time Memory were made and found to be highly reliable. The results of the forecast also showed an uptrend movement up to a price of around $275 from November 2023 to January 2024. In conclusion, the LSTM-RNN is capable of accurately tracking and forecasting movements of volatile stock prices and is preferred over the other models considered in this study.


. W. Bao, J. Yue, & Y. Rao, Y. “A deep learning framework for financial time series using stacked autoencoders and long-short-term memory”. PLOS ONE, 12(7), (2017).

. G.E. Box, & G. Jenkins, “Time Series Analysis, Forecasting, and Control”, (June, 1976).

. W. Leigh, R. Hightower, & N. Modani, “Forecasting the New York Stock Exchange composite index with past price and interest rate on condition of volume spike”, Expert Systems with Applications, 28(1), 1–8, (2005).

. Q. Wu, Y. Chen & Z. Liu, “Ensemble model of intelligent paradigms for stock market forecasting,” Proceedings of the IEEE 1st International Workshop on Knowledge Discovery and Data Mining, (2008), 205-208.

. R. Samsudin, A. Shabri, & P. Saad, “A Comparison of Time Series Forecasting using Support Vector Machine and Artificial Neural Network Model.” Journal of Applied Sciences, 10(11), 950–958, (2010).

. J. E. Jarrett, & E. Kyper, “ARIMA Modeling with Intervention to Forecast and Analyze Chinese Stock Prices.” International Journal of Engineering Business Management, 3(17), (2011).

. K.C. Tseng, O. Kwon, & L.C. Tjung, “Time series and neural network forecast of daily stock prices.” Investment Management and Financial Innovations, 9(1), 32 – 54, (2012).

. A.A. Adebiyi, A.O. Adewumi, & C.K. Ayo, “Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction.” Journal of Applied Mathematics, 4(1), 34-43, (2014).

. A.E. Soray, A. Zahra, & M. Ghiami, “Prediction of stock price using artificial neural network.” Bulletin de la Societe Royale des Sciences, 85, 991-998, (2010).

. S. Kumar, & L. Kumar, “Testing of Market Efficiency in India a Study of Random Walk Hypothesis of Indian Stock Market (BSE).” SSRN Electronic Journal, 35, 23 – 35, (2010).

. S. Roy, “Testing Random Walk and Market Efficiency: A Cross-Stock Market Analysis.” Foreign Trade Review, 53(4), 225–238, (2018).

. J. Israt “Stock Price Prediction Using Recurrent Neural Networks.” Graduate Faculty of the North Dakota State University of Agriculture and Applied Science, (2018)

. Q. Ma, “Comparison of ARIMA, ANN, and LSTM for Stock Price Prediction.” E3S Web of Conferences, (2020), 21 – 28. 01026.

. J. Shen, & M.O. Shafiq, “Short-term stock market price trend prediction using a comprehensive deep learning system.” Journal of Big Data, 7(1), 56 – 67, (2020).

. S. Mehtab, & J. Sen, “A time series analysis-based stock price prediction using machine learning and deep learning models.” International Journal of Business Forecasting and Marketing Intelligence, 6(4), 27 - 42, (2020).

. R. Subba et al. “Stock Market Prices Prediction Using Random Forest and Extra Tree Regression.” International Journal of Recent Technology and Engineering (IJRTE), 8(3), Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP, pp. 1224–28, (Sept. 2019). Crossref, doi:10.35940/ijrte.c4314.098319.

. M. Azizah, M.I. Irawan, & E.R.M. Putri, “Comparison of stock price prediction using geometric Brownian motion and multilayer perceptron”, Proceedings of the 5th International Symposium On Current Progress In Mathematics And Sciences (ISCPMS2019), (2020).

. A. Majumder, M.M. Rahman, A.A. Biswas, M.S. Zulfiker, & S. Basak, “Stock Market Prediction: A Time Series Analysis.” Smart Systems: Innovations in Computing, 389–401, 6, (2021).

. S.M. Farahani, & S.H.R. Hajiagha, “Forecasting Stock Price Using Integrated Artificial Neural Network and Meta-heuristic Algorithms Compared to Time Series Models.” Soft Computing, 25(13), 8483 – 8513, (2021). Crossref, doi:10.1007/s00500-021-05775-5.

. S. Shriram, K. Anuradha, K.P. & K.P. Uma, “Future Stock Price Prediction using Recurrent Neural Network, LSTM and Machine Learning.” International Journal of Engineering Research & Technology (Ijert) Icradl, 9(5), 78 – 101, (2021).

. C. Dani, (2023). Better Growth Stock: Apple vs. Microsoft.

. P. Selva, “Complete Guide to Time Series Forecasting in Python.” Retrieved from, (2021).

. D.C. Bartholomew, U.C. Orumie, C.P. Obite, I.B. Duru, & F.C. Akanno, “Modeling the Nigerian Bonny Light Crude Oil Price: The Power of Fuzzy Time Series.” Open Journal of Modeling and Simulation, 09(04), 370–390, (2021).

. C.C. Nwaigwe, G.U. Atuzie, I.C. Obinwanne, & C.J. Ogbonna, “A time series analysis of daily exchange rate of U.S dollar to naira from 2016-2017(recession period).” International Journal of Engineering and Scientific Research, Vol. 9(6), 36 – 43, (2018).

. C.P. Obite, U.I. Nwosu, & D.C. Bartholomew, “Modeling US Dollar and Nigerian Naira Exchange Rates During COVID-19 Pandemic Period: Identification of a High-performance Model for New Applications.” Journal of Mathematics and Statistics Studies, 2(1), 40–52, (2021).

. D.C. Bartholomew, C.C. Nwaigwe, U.C. Orumie, & G.O. Nwafor, “Intervention Analysis of COVID-19 Vaccination in Nigeria: The Naive Solution Versus Interrupted Time Series.” Annals of Data Science, 1 – 26, (2023).

. A. Marketa A. and F. Darina, “Selection of unit test based on length of the time series and value of AR(1) parameter.” STATISTIKA, 96 (3), 45 – 65, (2016).

. R.F. Engle, "Autoregressive Conditional Heteroskedasticity with Estimates of the Variance of United Kingdom Inflation". Econometrica. 50 (4): 987–1007, (1982). doi:10.2307/1912773. JSTOR 1912773.

. L.C. Lim, & S.K. Sek, “Comparing the Performances of GARCH-type Models in Capturing the Stock Market Volatility in Malaysia.” Procedia Economics and Finance, 5, 478–487, (2013).

. T. Maryam, & T.V. Ramanathan, “An overview of FIGARCH and related time series model.” Austrian Journal of Statistics, 41(3), 175-196, (2012).

. J.A. Omorogbe, & C.E. Ucheoma, “An application of asymmetric GARCH models on the volatility of bank equity in Nigeria's stock market” CBN Journal of Applied Statistics, 8(1), 73-99, (2017).

. O.O. Cyprian, et al. “Using Conditional Extreme Value Theory to Estimate Value-at-Risk for Daily Currency Exchange Rates.” Journal of Mathematical Finance, 7(4), 846 – 870, (2017). doi:10.4236/jmf.2017.74045.

. L. Wiri, & P. Sibeate, “A comparative study of Fourier series models and Seasonal ARIMA model of rainfall data in Portharcourt.” Asian Journal of Probability and Statistics, 10(31), 36-46, (2020).

. T. Bollerslev, "Generalized Autoregressive Conditional Heteroskedasticity". Journal of Econometrics. 31 (3), 307–327, (1986). doi:10.1016/0304-4076(86)90063-1. S2CID 8797625.

. D.G. Robert & D. Hager, “Handbook of Medical Image Computing and Computer-Assisted Intervention.” (2020).

. S. Haykin, “Neural Networks and Learning Machines.” Bowker, (2008). doi:10.1604/9780131471399.

. N. Shajun, & M. Nagoor, “Handbook of Deep Learning in Biomedical Engineering.” (2021).

. H. Seng, W. Arya, Q. Abdul, & M. Khaliq, “Comparative analysis of three recurrent neural networks.” Journal of Big Data, 9(50), 56 – 74, (2022).

. C.P. Obite, D.C. Bartholomew, U.I. Nwosu, G.E. Esiaba, & L.C. Kiwu, “The Optimal Machine Learning Modeling of Brent Crude Oil Price.” Quarterly Journal of Econometrics Research, 7(1), 31-43, (2021).

. P.R. Hansen, A. Lunde, & J.M. Nason, “The Model Confidence Set.” Econometrica, 79(2), 453–497, (2011).




How to Cite

Chrysogonus Chinagorom Nwaigwe, Desmond Chekwube Bartholomew, Emmanuel Chigozie Umeh, Godwin Onyeka Nwafor, Ibrahim Adamu, & Simplicius Chidiebere Oguguo. (2023). Modeling of the Microsoft Stock Prices Using Machine Learning and Classical Models: Identification of Optimal Model for Application. International Journal of Formal Sciences: Current and Future Research Trends, 20(1), 43–68. Retrieved from