SARIMA-ARCH versus genetic programming in stock price prediction

Abstract

In financial time series, one of the most challenging problems is predicting stock prices since the data generally exhibit deviation from the assumptions of stationary and homoscedasticity. For homogenous non-stationary time series, the Autoregressive Integrated Moving Average (ARIMA) model is the most commonly used linear class including some transformation such as differencing and variance stabilizing process. However, stock market data is often nonlinear, which indicates that more advanced methods are necessary. Genetic Programming (GP) is one of the evolutionary computational methods that could capture both linear and nonlinear patterns in time series data. The present study aims to build a machine learning tool using GP for prediction The Istanbul Stock Exchange National 100 (XU100) index and compare the obtained results with conventional seasonal ARIMA(SARIMA) and ARCH models. In order to achieve this goal, it was first modeled with the SARIMA model after appropriate transfor- mations were made to the stock price series and the diagnostic control result showed that the residual of the SARIMA model have the heteroscedasticity problem. Then, the ARCH model was applied to SARIMA residuals to eliminate this effect and an integrated SARIMA-ARCH model is obtained. Since it is possible and capable to model nonlinear and non-stationary time series using GP without any pre-assumptions, we proposed GP to predict the stock price series. The function set of GP consists of not only arithmetic but also trigonometric functions. To the best of our knowledge, this study is the first to predict XU100 stock price data using GP. In this experiment, the data set consists of the daily closing prices of the XU100 index over 775 days from the beginning of 2017 until the end of January 2020. The experimental results obtained show that the accuracy metrics used in the study are lower in the proposed GP model compared to other models. These results reveal that the GP method provides better predictive results for the financial time series data of the XU100 index than traditional methods.

Keywords

• Genetic Programming
• XU100
• SARIMA
• ARCH
• Stock Price Prediction

References

1. [1] Newbold, P. ARIMA model building and the time series analysis approach to forecasting. J Forecast 1983;2: 23-35.
2. [2] Box GE, Jenkins GM. Time Series Analysis: Forecasting and Control. California: Holden-Day; 1976.
3. [3] Hipel KW, McLeod AI. Time Series Modelling of Water Resources and Environmental Systems. Netherlands: Elsevier; 1994.
4. [4] Hanke JE, Wichern DW. Business Forecasting. 9th ed. New Jersey; 2009.
5. [5] Petrică AC, Stancu S, Tindeche A. Limitation of ARIMA models in financial and monetary economics. Theoret Appl Econ 2016;23:19-42.
6. [6] Priestley MB. Non-linear and Non-stationary Time Series Analysis. London: Academic Press; 1988.
7. [7] Guresen E, Kayakutlu G, Daim TU. Using artificial neural network models in stock market index prediction. Expert Syst Appl 2011;38:10389-97.
8. [8] Göçken M, Özçalıcı M, Boru A, Dosdoğru AT. Integrating metaheuristics and artificial neural networks for improved stock price prediction. Expert Syst Appl 2016;44:320-31.

9. [9] Oztekin A, Kizilaslan R, Freund S, Iseri A. A data analytic approach to forecasting daily stock returns in an emerging market. Eur J Oper Res 2016;253:697-710.
10. [10] Sarıca B, Eğrioğlu E, Aşıkgil B. A new hybrid method for time series forecasting: AR–ANFIS. Neural Comput Appl 2018;29:749-60.
11. [11] Henrique BM, Sobreiro VA, Kimura H. Stock price prediction using support vector regression on daily and up to the minute prices. J Finance Data Sci 2018;4:183-201.
12. [12] Song Y, Lee JW, Lee J. A study on novel filtering and relationship between input-features and target-vectors in a deep learning model for stock price prediction. Appl Intell 2019;49:897-911.
13. [13] Göçken M, Özçalıcı M, Boru A, Dosdoğru AT. Stock price prediction using hybrid soft computing models incorporating parameter tuning and input variable selection. Neural Comput Appl 2019;31:577-92.
14. [14] Jiang XQ, Zhang LC. Stock price fluctuation prediction method based on time series analysis. Discrete Cont Dyn-S 2019;12: 915-27.
15. [15] Yu P, Yan X. Stock price prediction based on deep neural networks. Neural Comput Appl 2020;32:1609-28.
16. [16] Cheng C, Sa-Ngasoongsong A, Beyca O, Le T, Yang H, Kong Z, Bukkapatnam ST. Time series forecasting for nonlinear and non-stationary processes: A review and comparative study. IIE Trans 2015;47:1053-71.
17. [17] Koza JR. Genetic Programming: On the Programming of Computers by Means of Natural Selection. USA: MIT Press; 1992.
18. [18] Kaboudan MA. Genetic programming prediction of stock prices. Comput Econ 2000;16:207-36.
19. [19] Duan M, Povinelli RJ. Estimating Time Series Predictability Using Genetic Programming. Proc. Artificial Neural Networks in Engineering, 2001, p. 215-20.
20. [20] Kľúčik M, Juriova J, Kľúčik M. Time Series Modeling with Genetic Programming Relative to ARIMA Models. Proc. Conference on New Techniques and Technologies for Statistics. NTTS2009, 2009, p. 17-27.
21. [21] Lee YS, Tong LI. Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming. Knowl Based Syst 2011;24:66-72.
22. [22] Claveria O, Monte E, Torra S. Evolutionary computation for macroeconomic forecasting. Comput Econ 2019;53:833-49.
23. [23] Guresen E, Kayakutlu G, Daim TU. Using artificial neural network models in stock market index prediction. Expert Syst Appl 2011;38:10389-97.
24. [24] Engle RF. Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica 1982:987-1007.
25. [25] Bollerslev T. Generalized autoregressive conditional heteroskedasticity. J Econom 1986;31:307-27.