İSLAMİ VE GELENEKSEL ENDEKSLERDE FİYAT TAHMİNİ: HİPERPARAMETRE OPTİMİZASYONU İLE HİBRİT MODEL ÖNERİLERİ

Abstract

Hisse senedi fiyat tahmini karmaşık, durağan ve doğrusal olmayan bir zaman serisi tahminidir ve birçok faktörden etkilenmektedir. Bu durum da hisse senetlerinin gelecek fiyat tahminlerinin basit modellerle tahmin edilmesini zorlaştırabilmektedir. Dolayısıyla piyasa katılımcılarının kayıpları en aza indirmek ve karlarını maksimize etmek amacıyla bilinçli karar almaya çalıştıkları bu karmaşık ve dinamik piyasada, fiyatların doğru tahmini büyük önem arz etmektedir. Bu motivasyonla çalışmada İslami ve geleneksel kriterlerle oluşturulmuş seçili endekslerin gelecek fiyatlarının tahmin edilmesi ve en başarılı modelin tespit edilerek piyasa katılımcılarına fiyat tahminlemesi için model önerisi getirilmesi amaçlanmaktadır. Bu kapsamda, çalışmada 6 geleneksel, 6 İslami olmak üzere 12 Endeks ARIMA, XGBoost, LSTM ve Karar Ağacı yöntemleri ile analiz edilmiştir. Analizler neticesinde makine öğrenimi modellerinin gelenekseldendaha üstüm performans gösterdiği tespit edilmiştir. Bu bulgularla elde edilen en iyi parametreler aracılığıyla XGBoost-Karar Ağacı, LSTM- XGBoost ve LSTM-Karar Ağacı hibrit modelleri oluşturulmuştur. Bu doğrultuda optimize edilen hiper parametreler ile 1 geleneksel, 3 makine öğrenimi ve 3 hibrit model olmak üzere 7 algoritma ile 12 Endeks toplamda 84 farklı modelle analiz edilmiştir. Model performansını ölçmek için RMSE değerleri tespit edilmiş ve geliştirilen hibrit modeller kapsamında BİST Katılım 100 Endeksi’nde LSTM-Karar Ağacı; diğer tüm Endekslerde ise LSTM-XGBoost modelinin en iyi tahminci olduğu sonucuna ulaşılmıştır.

Keywords

• Tahminleme
• XGBoost
• LSTM
• Karar Ağacı
• Hibrit model.

PRICE FORECASTING IN ISLAMIC AND CONVENTIONAL INDICES: HYBRID MODEL PROPOSALS WITH HYPERPARAMETER OPTIMIZATION

Abstract

Stock price forecasting is a complex, stationary, and nonlinear time series estimation problem influenced by numerous factors. This complexity renders basic models inadequate for producing accurate forecasts of future stock prices.. Thus, precise price forecasting is crucial in this intricate and dynamic market where participants strive to make well-informed decisions to minimize losses and maximize profits. Motivated by this necessity, the present study aims to forecast future prices of selected indices constructed according to both Islamic and traditional criteria and to propose the most effective forecasting model for market participants. . Twelve indices- six traditional and six Islamic- were examined in this context using the ARIMA, XGBoost, LSTM, and Decision Tree methods. The investigation revealed that machine learning models outperformed the conventional approaches in terms of outcomes. The optimal parameters were then acquired and XGBoost-Decision Tree, LSTM-XGBoost, and LSTM-Decision Tree hybrid models were developed based on the results obtained. In this regard, 84 distinct models with seven algorithms- 1 conventional, 3 machine learning, and 3 hybrid models- with optimized hyperparameters were applied to the 12 indices. RMSE values were used to evaluate model performance. The LSTM-Decision Tree model was shown to be the greatest predictor for the BIST Participation 100 Index, while the LSTM-XGBoost model was the best predictor for all other indices.

Keywords

• Forecasting
• XGBoost
• LSTM
• Decision Tree
• Hybrid model.

References

1. Ariyo, A., Adewumi, A., & Ayo, C. (2014). Stock price prediction using the ARIMA model. In 2014 UKSim-AMSS 16th international conference on computer modelling and simulation (s. 106-112). IEEE.
2. Bhattacharjee, I., & Bhattacharja, P. (2019). Stock Price Prediction: A Comparative Study between Traditional Statistical Approach and Machine Learning Approach. 4th International Conference on Electrical Information and Communication Technology (EICT). IEEE.
3. Dai, Y., Zhou, Q., Leng, M., Yang, X., & Wang, Y. (2022). Improving the Bi-LSTM model with XGBoost and attention mechanism: A combined approach for short-term power load prediction. Applied Soft Computing, 130. doi:https://doi.org/10.1016/j.asoc.2022.109632
4. Göğen, E., & Güney, S. (2024). Machine learning-based weather prediction with radiosonde observations. Journal of the Faculty of Engineering and Architecture of Gazi University, 39(4), 2317-2328. doi:10.17341/gazimmfd.1163079
5. Han, C., & Fu, X. (2023). Challenge and Opportunity: Deep Learning-Based Stock Price Prediction by Using Bi-Directional LSTM Model. Frontiers in Business, Economics and Management, 8(2), 51-54.
6. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation. 9(8), 1735–1780. Hossain, M., Karim, R., Thulasiram, R., Bruce, N., & Wang, Y. (2018). Hybrid deep learning model for stock price prediction. In 2018 ieee symposium series on computational intelligence (ssci) (s. 1837-1844). IEEE.
7. Jijo, B., & Abdulazeez, A. (2021). Classification Based on Decision Tree Algorithm for Machine Learning. ournal of Applied Science and Technology Trends, 2(1), 20-28.
8. Jing, N., Wu, Z., & Wang, H. (2021). A hybrid model integrating deep learning with investor sentiment analysis for stock price prediction. Expert Systems with Applications, 178. doi:https://doi.org/10.1016/j.eswa.2021.115019

9. Kabir, M., Sobur, A., & Amin, M. (2023). Stock Price Prediction Using the Machine Learning. nternational Journal of Computer Research and Technology (IJCRT), 11(7), 946-950.
10. Karim, R., Alam, M., & Hossain, M. (2021). Stock market analysis using linear regression and decision tree regression. In 2021 1st International. In 2021 1st International Conference on Emerging Smart Technologies and Applications (eSmarTA) (s. 1-6). IEEE.
11. Kumar, D., Thiruvarangan, B., Reddy C, S., Vishnu, A., Devi, A., & Kavitha, D. (2022). Analysis and prediction of stock price using hybridization of sarima and xgboost. In 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT) (s. 1-4). IEEE.
12. Li, L., Wu, Y., Ou, Y., Li, Q., Zhou, Y., & Chen, D. (2017). Research on machine learning algorithms and feature extraction for time series. In 2017 IEEE 28th annual international symposium on personal, indoor, and mobile radio communications (PIMRC) (s. 1-5). IEEE.
13. Liwei, T., Li, F., Yu, S., & Yuankai, G. (2021). Forecast of LSTM-XGBoost in Stock Price Based on Bayesian Optimization. Intelligent Automation & Soft Computing, 29(3), 855-868. doi:http://dx.doi.org/10.32604/iasc.2021.016805
14. Manasa, M., & Reddy, A. (2024). Stock Market Prediction Using Machine Learning and Deep Learning Algorithms. UGC Care Group I Listed Journal, 14(1), 49-60.
15. Mehak, U., Adil, S., Raza, K., & Ali, S. (2016). Stock Market Prediction Using Machine Learning Techniques. 2016 3rd International Conference On Computer and Information Sciences (ICCOINS) (s. 322-327). IEEE.
16. Miah, M., Hossain, M., Hossain, M., & Islam, M. (2015). Price prediction of stock market using hybrid model of artificial intelligence. International Journal of Computer Applications, 111(3).
17. Oukhouya, H., & Himdi, K. (2023). Comparing machine learning methods—svr, xgboost, lstm, and mlp—for forecasting the moroccan stock market. Computer Sciences & Mathematics Forum, 7(1), 39.
18. Oukhouya, H., Kadiri, H., Himdi, K., & Guerbaz, R. (2024). Forecasting International Stock Market Trends: XGBoost, LSTM LSTM-XGBoost, And Backtesting XGBoost Models. (200-209, Dü.) Statistics, Optimization & Information Computing, 12(1).
19. Qihang, M. (2020). Comparison of ARIMA, ANN and LSTM for stock price prediction. In E3S Web of Conferences. EDP Sciences.
20. Somkunwar, R., Pimpalkar, A., & Srivastava, V. (2024). A Novel Approach for Accurate Stock Market Forecasting by Integrating ARIMA and XGBoost. In 2024 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS) (s. 1-6). IEEE.
21. Tong, Z., Li, H., & Zhang, Y. (2023). A Comparison of ARIMA, LSTM, XGBOOST and Hybrid in Stock Price Prediction. In 2023 5th International Conference on Applied Machine Learning (ICAML) (s. 18-25). IEEE.
22. Tsai, C., & Wang, S. (2009). Stock price forecasting by hybrid machine learning techniques. In Proceedings of the international multiconference of engineers and computer scientists, Vol.1 No.755, s. 60.
23. Xiao, C., Xia, W., & Jiang, J. (2020). Stock price forecast based on combined model of ARI-MA-LS-SVM. Neural Computing and Applications, 32(10), 5379-5388. doi:https://doi.org/10.1007/s00521-019-04698-5
24. Zhang, J., Liu, H., Bai, W., & Li, X. (2024). A hybrid approach of wavelet transform, ARIMA and LSTM model for the share price index futures forecasting. The North American Journal of Economics and Finance, 69. doi:https://doi.org/10.1016/j.najef.2023.102022
25. Zhu, R., Zhong, G.-Y., & Li, J.-C. (2024). Forecasting price in a new hybrid neural network model with machine. Expert Systems with Applications, 249. doi:https://doi.org/10.1016/j.eswa.2024.123697