Simulation analysis of artificial neural network and XGBoost algorithms in time series forecasting

• Autorzy: Sroka Łukasz

Identyfikatory

DOI

10.29119/1641-3466.2024.195.34

• Języki publikacji: EN

Abstrakty

EN

Purpose: The aim of the article was to prepare a simulation analysis of artificial neural network and XGBoost algorithm with determining which of the method was characterized by a lower level of forecast errors for time series predictions. Design/methodology/approach: The objective of the article was reached by applying, a simulation study on a sample of 1000 artificially generated time series. The analyzed XGBoost algorithm and the artificial neural network ANN model were intended to prepare forecasts for five periods ahead. These forecasts were compared with the actual implementations of the time series and proposed forecast error measures. Findings: It is possible to use simulated time series to check which of the presented algorithms were characterized by a lower forecast error. The study showed that applying of the artificial neural networks ANN to forecast future observations generated a lower level of MAPE, MAE and RMSE errors than in the case of the XGBoost algorithm. It was found that both methods generate a lower level of forecast error for time series characterized by a high level of mean value, standard deviation and variance, and levels of kurtosis and skewness close to 0. Practical implications: The research results can be used by both investors and enterprises to better adjust their business decisions to changing market prices by using a model with a lower forecast bias. Originality/value: The original contribution of this article is a comprehensive comparison of forecasts generated by the XGBoost and ANN algorithm, along with determining for which types of time series of the algorithms forecast future values with less error. Moreover, due to the use of simulated artificial time series, it was possible to test each algorithm for various market conditions.

Słowa kluczowe

EN

artificial neural network; XGBoost; time series; forecasting; simulation

PL

sztuczna sieć neuronowa; XGBoost; szereg czasowy; prognozowanie; symulacja

• Wydawca: Wydawnictwo Politechniki Śląskiej
• Czasopismo: Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska
• Rocznik: 2024
• Tom: z. 195
• Strony: 561--575
• Opis fizyczny: Bibliogr. 26 poz.

Twórcy

autor

Sroka Łukasz

• University of Economics in Katowice

• https://orcid.org/0000-0001-5721-2475

Bibliografia

• 1. Adebiyi, A., Adewumi, A., Ayo, C. (2014). Stock price prediction using the ARIMA model. Proceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, pp. 106-112.
• 2. Al-Thanoon, N.A., Algamal, Z.Y., Qasim, O.S. (2022). Hyper Parameters Optimization of Support Vector Regression Based on a Chaotic Pigeon-Inspired Optimization Algorithm. Mathematical Statistician and Engineering Applications, Vol. 71, No. 4, pp. 4997-5008.
• 3. Ben Jabeur, S., Mefteh-Wali, S., Jean-Laurent, V. (2021). Forecasting gold price with the XGBoost algorithm and SHAP interaction values. Annals of Operations Research.
• 4. Biswas, M., Shome, A., Islam, A., Ahmed, S. (2021). Predicting Stock Market Price: A Logical Strategy using Deep Learning. 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), pp. 218-223.
• 5. Cai-Xia, L., Shu-Yi, A., Bao-Jun, Q., Wei, W. (2021). Time series analysis of hemorrhagic fever with renal syndrome in mainland China by using an XGBoost forecasting model. BMC Infect. Dis., Vol. 21, No. 1, p. 839.
• 6. Chen, Y., Hao, Y. (2017). A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction. Expert Systems with Applications, No. 80, pp. 340-355.
• 7. Chung, H., Shin, K. (2020). Genetic algorithm-optimized multi-channel convolutional neural network for stock market prediction. Neural Computing and Applications, Vol. 32, No. 12, pp. 7897-7914.
• 8. Gao, G., Kwoklun, L., Fulin, F. (2017). Comparison of ARIMA and ANN Models Used in Electricity Price Forecasting for Power Market. Energy and Power Engineering, No. 9, pp. 120-126.
• 9. Grabowska, E. (2019). Jak udoskonalić algorytm drzew decyzyjnych? Predictive Solution, from: https://predictivesolutions.pl/jak-udoskonalic-algorytm-drzew-decyzyjnych
• 10. Kim, T., Kim Ha, Y. (2019). Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data. PLoS ONE 2019, Vol. 14, No. 2.
• 11. Kyung, K., Yun, S., Won, Y., Daehan, W. (2021). Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process. Expert Systems with Applications, No. 186.
• 12. Latrisha, M., Jeta, H., Callista, A., Said, A., Aditya, K. (2023). Machine learning approaches in stock market prediction: A systematic literature review. Procedia Computer Science, No. 216, pp. 96-102.
• 13. Li, R., Han, T., Song, X. (2022). Stock price index forecasting using a multiscale modelling strategy based on frequency components analysis and intelligent optimization. Applied Soft Computing, Vol. 124, No. 2.
• 14. Martinović, M., Anica, H., Ioan, T. (2020). Time Series Forecasting of the Austrian Traded Index (ATX) Using Artificial Neural Network Model. Tehnički vjesnik, Vol. 6, No. 27, pp. 2053-2061.
• 15. Mo, H., Sun, H., Liu, J., Wei, S. (2019). Developing window behavior models for residential buildings using XGBoost algorithm. Energy and Buildings, No. 205.
• 16. Nagaraj, N., Mohan, B.R. (2019). Stock Price Movements Classification Using Machine and Deep Learning Techniques-The Case Study of Indian Stock Market. International Conference on Engineering Applications of Neural Networks. Springer International Publishing, pp. 445-452.
• 17. Ord, K., Balkin, S. (2000). Automatic neural network modeling for univariate time series. International Journal of Forecasting, No. 16, pp. 509-515.
• 18. Osowski, S. (2006). Sieci neuronowe do przetwarzania informacji. Warszawa: OW PW.
• 19. Oukhouya, H., Khalid El Himd (2023). Comparing Machine Learning Methods—SVR, XGBoost, LSTM, and MLP— For Forecasting the Moroccan Stock Market. Computer Sciences & Mathematics Forum, 7, No. 1.
• 20. Ozbayoglu, A., Murat, G., Mehmet, U.S., Omer, B. (2020). Deep learning for financial applications: A survey. Appl. Soft Comput., No. 93.
• 21. Sarapata, M. (2014). Prognozowanie finansowych szeregów czasowych z wykorzystaniem modeli jednokierunkowych sieci neuronowych. In: W. Szkutnik (ed.), Studia Ekonomiczne (pp. 114-126). Katowice: Wydawnictwo Uniwersytetu Ekonomicznego.
• 22. Tadeusiewicz, R., Szaleniec, M. (2015). Leksykon sieci neuronowych. Wrocław: Projekt Nauka. Fundacja Na Rzecz Promocji Nauki Polskiej.
• 23. Wang, Q., Xu, W., Zheng, H. (2018). Combining the wisdom of crowds and technical analysis for financial market prediction using deep random subspace ensembles. Neurocomputing, No. 299, pp. 51-61.
• 24. Witkowska, D. (2002). Sztuczne sieci neuronowe i metody statystyczne: wybrane zagadnienia finansowe. Warszawa: C.H.Beck.
• 25. Yamin, H.Y., Shahidehpour, S.M., Zuyi, L. (2004). Adaptive short-term electricity price forecasting using artificial neural networks in the restructured power markets. International journal of electrical power & energy systems, Vol. 26, No. 8, pp. 571-581.
• 26. Zhang, Y. (2022). Stock Price Prediction Method Based on XGboost Algorithm. International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022).