AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING

Mustafa Etcil; Burak Kolukisa; Burcu Güngör

TR EN

TEMEL ORANLAR KULLANILARAK HISSE SENEDI GETIRI TAHMINI VE PORTFÖY YENIDEN DENGELEME IÇIN AÇIKLANABILIR BIR MAKINE ÖĞRENIMI YAKLAŞIMI

Öz

Bu çalışma, hisse senetlerinin piyasa göreli performansını tahmin etmek ve Borsa İstanbul’da (BIST) portföy yeniden dengelemesini yönlendirmek amacıyla açıklanabilir ensemble öğrenme çerçevesi geliştirmektedir. Analiz, 2009-Q1–2025-Q1 döneminde 20 firmanın çeyreklik verilerini kapsamakta ve on üç finansal oranla eğitilen Random Forest, XGBoost, LightGBM ve CatBoost algoritmalarını kullanmaktadır. Hiperparametreler zaman serisi çapraz doğrulamalı grid search ile seçilmekte, performans örneklem dışı dönemde değerlendirilmektedir. Portföyler tahmin edilen getirilere göre çeyreklik yeniden dengelenmekte ve eşit ağırlıklı portföy ile BIST 100 Endeksi’yle karşılaştırılmaktadır. Bulgular, model tabanlı portföylerin toplam getiri ve risk ayarlı performansta karşılaştırma stratejilerini geride bıraktığını; daha güçlü ve istatistiksel olarak desteklenen sonuçların geniş Top-k konfigürasyonlarında, özellikle CatBoost Top-7’de görüldüğünü göstermektedir. SHAP analizi, aktif kârlılığı, özkaynak kârlılığı ve temel değerleme oranlarını gelecekteki hisse performansının başlıca belirleyicileri olarak göstermektedir.

Anahtar Kelimeler

Destekleyen Kurum

Tubitak

Proje Numarası

3230482

Etik Beyan

Bu araştırma, TÜBİTAK TEYDEB programı kapsamında 3230482 numaralı proje ile desteklenen "Sosyal Medya, Haber, Temel ve Teknik Analizleri Dikkate Alan Makine Öğrenmesi Temelli Hisse Senedi Yatırım Tavsiye Platformu" başlıklı proje tarafından desteklenmiştir.

AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING

Öz

This research develops an explainable ensemble learning framework to forecast stocks’ market-relative performance and guide portfolio rebalancing in Borsa Istanbul (BIST). The analysis covers quarterly data from 20 firms between 2009-Q1 and 2025-Q1 and employs Random Forest, XGBoost, LightGBM, and CatBoost trained on thirteen financial ratios. Hyperparameters are selected using grid search with time-series cross-validation, and performance is evaluated out-of-sample. Portfolios are rebalanced quarterly using predicted returns and benchmarked against an equally weighted portfolio and the BIST 100 Index. Results show that model-based portfolios generally outperform benchmarks in total return and risk-adjusted performance, with stronger statistically supported results in broader Top-k configurations, particularly CatBoost Top-7. SHAP identifies profitability and valuation indicators, especially return on assets, return on equity, and key valuation ratios, as the main drivers of future stock performance. These findings support explainable ensemble learning for fundamental-based portfolio management in emerging markets.

Anahtar Kelimeler

Destekleyen Kurum

Tubitak

Proje Numarası

3230482

Etik Beyan

This research was supported by the project titled "Sosyal Medya, Haber, Temel ve Teknik Analizleri Dikkate Alan Makine Öğrenmesi Temelli Hisse Senedi Yatırım Tavsiye Platformu" funded by the TUBITAK TEYDEB program under Project Number 3230482.

Kaynakça

Basak, S., Kar, S., Saha, S., Khaidem, L., & Dey, S. R. (2019). Predicting the direction of stock market prices using tree-based classifiers. The North American Journal of Economics and Finance, 47, 552–567. https://doi.org/10.1016/j.najef.2018.06.013.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324 Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785.
Dai, T. S., Chen, B. J., Sun, Y. J., Yang, D. Y., & Wu, M. E. (2024). Constructing optimal portfolio rebalancing strategies with a two-stage multiresolution-grid model. Computational Economics, 64(5), 3117–3142. https://doi.org/10.1007/s10614-024-10555-y.
Fabozzi, F. J., & Markowitz, H. M. (Eds.). (2011). The theory and practice of investment management: Asset allocation, valuation, portfolio construction, and strategies (2nd ed.). John Wiley & Sons. https://doi.org/10.1002/9781118267028.
Financial Modeling Prep. Financial Modeling Prep API: Documentation V2 – API Reference. (2024). https://site.financialmodelingprep.com/developer/docs/ Accessed 04.05.25.
Gunjan, A., & Bhattacharyya, S. (2023). A brief review of portfolio optimization techniques. Artificial Intelligence Review, 56(5), 3847–3886. https://doi.org/10.1007/s10462-022-10273-7.
Huang, M., Dang, S., & Bhuiyan, M. A. (2026). Multi-objective portfolio optimization for stock return prediction using machine learning. Expert Systems with Applications, 298, 129672. https://doi.org/10.1016/j.eswa.2025.129672.
Huang, Y., Capretz, L. F., & Ho, D. (2021). Machine learning for stock prediction based on fundamental analysis. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1–10). IEEE. https://doi.org/10.1109/SSCI50451.2021.9660134

Kalayci, C. B., Ertenlice, O., & Akbay, M. A. (2019). A comprehensive review of deterministic models and applications for mean–variance portfolio optimization. Expert Systems with Applications, 125, 345–368. https://doi.org/10.1016/j.eswa.2019.02.011.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30. https://papers.nips.cc/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html.
Krauss, C., Do, X. A., & Huck, N. (2017). Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500. European Journal of Operational Research, 259(2), 689–702. https://doi.org/10.1016/j.ejor.2016.10.031.
Liu, M., Luo, K., Zhang, J., & Chen, S. (2021). A stock selection algorithm hybridizing grey wolf optimizer and support vector regression. Expert Systems with Applications, 179, 115078. https://doi.org/10.1016/j.eswa.2021.115078.
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774. https://papers.neurips.cc/paper_files/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html.
Markowitz, H. M. (1991). Foundations of portfolio theory. The Journal of Finance, 46(2), 469–477. https://doi.org/10.1111/j.1540-6261.1991.tb02669.x.
Novykov, V., Bilson, C., Gepp, A., Harris, G., & Vanstone, B. J. (2025). Deep learning applications in investment portfolio management: A systematic literature review. Journal of Accounting Literature, 47(2), 245–276. https://doi.org/10.1108/JAL-07-2023-0119.
Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020). A systematic review of fundamental and technical analysis of stock market predictions. Artificial Intelligence Review, 53(4), 3007–3057. https://doi.org/10.1007/s10462-019-09754-z.
Paiva, F. D., Cardoso, R. T. N., Hanaoka, G. P., & Duarte, W. M. (2019). Decision-making for financial trading: A fusion approach of machine learning and portfolio selection. Expert Systems with Applications, 115, 635–655. https://doi.org/10.1016/j.eswa.2018.08.003.
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 31, 6638–6648. https://proceedings.neurips.cc/paper/2018/hash/14491b756b3a51daac41c24863285549-Abstract.html.
Silva, A., Neves, R., & Horta, N. (2015). A hybrid approach to portfolio composition based on fundamental and technical indicators. Expert Systems with Applications, 42(4), 2036–2048. https://doi.org/10.1016/j.eswa.2014.09.050.
Sutiene, K., Schwendner, P., Sipos, C., Lorenzo, L., Mirchev, M., Lameski, P., Kabasinskas, A., Tidjani, C., Ozturkkal, B., & Cerneviciene, J. (2024). Enhancing portfolio management using artificial intelligence: Literature review. Frontiers in Artificial Intelligence, 7, 1371502. https://doi.org/10.3389/frai.2024.1371502.
Tsai, P. F., Gao, C. H., & Yuan, S. M. (2023). Stock selection using machine learning based on financial ratios. Mathematics, 11(23), 4758. https://doi.org/10.3390/math11234758. yfinance. yfinance: Python Library for Yahoo! Finance Market Data. (2025). https://pypi.org/project/yfinance/ Accessed 18.08.25.
Zilbering, Y., Jaconetti, C. M., & Kinniry, F. M., Jr. (2015). Best practices for portfolio rebalancing. Valley Forge, PA: The Vanguard Group. https://www.financieelonafhankelijkblog.nl/wp-content/uploads/2021/11/Vanguard-ISGPORE.pdf

Ayrıntılar

Birincil Dil

İngilizce

Konular

Derin Öğrenme, Veri Mühendisliği ve Veri Bilimi

Bölüm

Araştırma Makalesi

Yazarlar

Mustafa Etcil ^*
0000-0002-5573-3418
Türkiye

Burak Kolukisa
0000-0003-0423-4595
Türkiye

Burcu Güngör
0000-0002-2272-6270
Türkiye

Yayımlanma Tarihi

3 Eylül 2026

Gönderilme Tarihi

22 Ekim 2025

Kabul Tarihi

24 Haziran 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 29 Sayı: 3

IZ

https://izlik.org/JA75SH66HP

Kaynak Göster

RIS / Bibtex

APA

Etcil, M., Kolukisa, B., & Güngör, B. (2026). AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 29(3), 1004-1019. https://izlik.org/JA75SH66HP

AMA

1.Etcil M, Kolukisa B, Güngör B. AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi. 2026;29(3):1004-1019. https://izlik.org/JA75SH66HP

Chicago

Etcil, Mustafa, Burak Kolukisa, ve Burcu Güngör. 2026. “AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29 (3): 1004-19. https://izlik.org/JA75SH66HP.

EndNote

Etcil M, Kolukisa B, Güngör B (01 Eylül 2026) AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29 3 1004–1019.

IEEE

[1]M. Etcil, B. Kolukisa, ve B. Güngör, “AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING”, Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, c. 29, sy 3, ss. 1004–1019, Eyl. 2026, [çevrimiçi]. Erişim adresi: https://izlik.org/JA75SH66HP

ISNAD

Etcil, Mustafa - Kolukisa, Burak - Güngör, Burcu. “AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29/3 (01 Eylül 2026): 1004-1019. https://izlik.org/JA75SH66HP.

JAMA

1.Etcil M, Kolukisa B, Güngör B. AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi. 2026;29:1004–1019.

MLA

Etcil, Mustafa, vd. “AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, c. 29, sy 3, Eylül 2026, ss. 1004-19, https://izlik.org/JA75SH66HP.

Vancouver

1.Mustafa Etcil, Burak Kolukisa, Burcu Güngör. AN EXPLAINABLE MACHINE LEARNING APPROACH USING FUNDAMENTAL RATIOS FOR STOCK RETURN PREDICTION AND PORTFOLIO REBALANCING. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi [Internet]. 01 Eylül 2026;29(3):1004-19. Erişim adresi: https://izlik.org/JA75SH66HP