OPTIMIZING TIME SERIES FORECASTING: LEVERAGING MACHINE LEARNING MODELS FOR ENHANCED PREDICTIVE ACCURACY
Waldemar Wójcik
Lublin University of Technology (Poland)
Assem Shayakhmetova
Al-Farabi Kazakh National University (Kazakhstan)
https://orcid.org/0000-0002-4072-3671
Ardak Akhmetova
Al-Farabi Kazakh National University (Kazakhstan)
Assel Abdildayeva
asselabdildayeva5@gmail.comAl-Farabi Kazakh National University (Kazakhstan)
https://orcid.org/0000-0002-6381-9350
Galymzhan Nurtugan
Al-Farabi Kazakh National University (Kazakhstan)
Abstract
Engaging in investment activities plays a crucial and strategic role in fostering the growth of businesses and ensuring their resilience in the market. This involvement entails expenditures on acquiring assets, embracing technological advancements, expanding production capacities, conducting research and development, among various other domains. Collectively, these aspects form the foundation for the sustained success of an organization over the long term. This thesis will delve into an exploration of leveraging machine learning techniques to forecast key parameters in business, including investments and their impact on the financial health of the company. In this research, explored a variety of time series models and identified that both the Random Forest Regressor and Decision Tree Regressor models deliver superior accuracy, showcasing identical RMSE values of 88.36 on the validation dataset. Furthermore, the Cat Boost and Light GBM models exhibited praiseworthy performance, registering RMSE values of 92.47 and 104.69, respectively. These findings highlight the robust performance of Random Forest Regressor and Decision Tree Regressor, emphasizing their capability to provide accurate predictions. It is noted that Random Forest Regressor and Decision Tree Regressor are distinguished by high accuracy in time series forecasting, and the choice between them should take into account the trade-offs between computational efficiency and interpretability of the model. These results allow us to propose practical strategies for managing investment resources to ensure the sustainable development and prosperity of the enterprise in the long term.
Keywords:
autoregression, ARIMA, time series, Decision Tree Regressor, Random Forest Regressor, Cat Boost RegressorReferences
[1] Adebiyi A. A. et al.: Comparison of ARIMA and artificial neural networks models for stock price prediction. Journal of Applied Mathematics, 2014, 2014.
Google Scholar
[2] Adebiyi A. A. et al.: Stock price prediction using the ARIMA model. UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, IEEE, 2014, 106–112.
Google Scholar
[3] Chia-Cheng C., Chun-Hung C., Ting-Yin L.: Investment performance of machine learning: Analysis of S&P 500 index. International Journal of Economics and Financial Issues 10(1), 2020, 59–66.
Google Scholar
[4] Deng Y. et al.: Deep direct reinforcement learning for financial signal representation and trading. IEEE Transactions on Neural Networks and Learning Systems 28(3), 2017, 653–664.
Google Scholar
[5] Gamboa J. C. B.: Deep learning for time-series analysis. 2017, arXiv:1701.01887.
Google Scholar
[6] Hyndman R. et al.: Forecasting with Exponential Smoothing. Springer, Berlin Heidelberg 2008.
Google Scholar
[7] Leung C. K.-S., MacKinnon R. K., Wang Y.: A machine learning approach for stock price prediction. 18th International Database Engineering & Applications Symposium – IDEAS'14, 2014, 274–277.
Google Scholar
[8] Nabipour M. et al.: Predicting stock market trends using machine learning and deep learning algorithms via continuous and binary data; a comparative analysis. IEEE Access 8, 2020, 150199-150212.
Google Scholar
[9] Nelson D., Pereira A., de Oliveira R.: Stock market’s price movement prediction with LSTM neural networks. IEEE International Joint Conference on Neural Networks (IJCNN). 2017, 1419–1426.
Google Scholar
[10] Qingsong W. et al.: Transformers in Time Series: A Survey. 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023), 2023.
Google Scholar
[11] Shi J. et al.: Time Series Forecasting (TSF) Using Various Deep Learning Models. World Academy of Science, Engineering and Technology. International Journal of Computer and Systems Engineering, 2022.
Google Scholar
[12] Smyl S.: A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. Int. J. Forecast. 36(1), 2020, 75–85.
Google Scholar
[13] Sutton R. S., Barto A. G.: Reinforcement learning – an introduction. Adaptive computation and machine learning. MIT Press, 2014.
Google Scholar
[14] Szepesvari C.: Algorithms for Reinforcement Learning. Morgan & Claypool Publishers, 4, 2010.
Google Scholar
[15] Usmani M. et al.: Stock market prediction using machine learning techniques. 3rd International Conference on Computer and Information Sciences. 2018, 146–158.
Google Scholar
[16] Vijh M. et al.: Stock Closing Price Prediction using Machine Learning Techniques. International Conference on Computational Intelligence and Data Science. 2022, 599–606.
Google Scholar
[17] Yawei L., Peipei L., Ze W.: Stock Trading Strategies Based on Deep Reinforcement. Learning Hindawi Scientific Programming. 2022, 1–15.
Google Scholar
[18] Zhang K. T. et al.: AlphaStock: A Buying-Winners-and-Selling-Losers Invest-ment Strategy using Interpretable Deep Reinforcement Attention Networks. Decision Support Systems, 2019, 14–28.
Google Scholar
Authors
Waldemar WójcikLublin University of Technology Poland
Authors
Assem ShayakhmetovaAl-Farabi Kazakh National University Kazakhstan
https://orcid.org/0000-0002-4072-3671
Authors
Ardak AkhmetovaAl-Farabi Kazakh National University Kazakhstan
Authors
Assel Abdildayevaasselabdildayeva5@gmail.com
Al-Farabi Kazakh National University Kazakhstan
https://orcid.org/0000-0002-6381-9350
Authors
Galymzhan NurtuganAl-Farabi Kazakh National University Kazakhstan
Statistics
Abstract views: 2PDF downloads: 3
Most read articles by the same author(s)
- Kuanysh Mussilimov, Akhmet Ibraev, Waldemar Wójcik, DEVELOPMENT OF WIND ENERGY COMPLEX AUTOMATION SYSTEM , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 9 No. 2 (2019)
- Waldemar Wójcik, Batyrbek Suleimenov, Gennadiy Shadrin, Mikhail Shadrin, Dmitriy Porubov, OPTIMAL CONTROL SYSTEM OF DIESEL AUTOMOTIVE ENGINEERING BY EXAMPLE OF OPEN PIT MOTOR TRANSPORT , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 4 No. 1 (2014)
- Olessya A. Yuchshenko, Waldemar Wójcik, DEVELOPMENT OF SIMULATION MODEL OF STRIP PULL SELF-REGULATION SYSTEM IN DYNAMIC MODES IN A CONTINUOUS HOT GALVANIZING LINE , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 4 No. 1 (2014)
- Shamil Koshymbaevich Koshymbaev, Zhibek Shegebaeva, Waldemar Wójcik, DEFINITION OF THE OBJECTS OF MULTIVARIABLE CONTROL OF TECHNOLOGICAL PROCESS OF SMELTING INDUSTRY ON THE BASIS OF OPTIMIZATION MODEL , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 4 No. 1 (2014)
