EXPLORING THE INTERPRETABILITY AND PREDICTIVE POWER OF MACHINE LEARNING MODELS IN TECHNOLOGY INDICES: A CASE STUDY

Öz

The paper is a comprehensive study of the performance evaluation of Aselsan in the Borsa Istanbul Technology Index, explaining the interpretability and predictability power of the machine learning models. The study encapsulates the technical indicators and the index data as variables and is conducted in a dataset of 600 days between November 20, 2020, and April 10, 2023. The data was split into two subsets, with 85% allocated to the training subset and 15% to the validation subset. Model training is conducted using the Orthogonal Matching Pursuit (OMP) algorithm. After the training, the model validates its prediction using previously unseen data. The results of the model's findings at this stage indicate the model's strong capacity to predict and robustly predict movements in Aselsan stock prices. Additionally, the model has an interpretability capacity that helps the user understand the decision process and the reasons behind the predictions.

Anahtar Kelimeler

• Interpretability
• Predictive Power
• Stock Price
• Machine Learning
• Technology Indices

TEKNOLOJİ ENDEKSLERİNDE MAKİNE ÖĞRENİMİ MODELLERİNİN YORUMLANABİLİRLİĞİNİN VE TAHMİN GÜCÜNÜN ARAŞTIRILMASI: BİR VAK’A ÇALIŞMASI

Öz

Bu çalışma, Aselsan'ın Borsa İstanbul Teknoloji Endeksi'ndeki performans değerlendirmesini, makine öğrenmesi modellerinin yorumlanabilirlik ve öngörülebilirlik gücünü açıklayan kapsamlı bir çalışmadır. Çalışma, teknik göstergeleri ve endeks verilerini değişkenler olarak içermekte olup, 20 Kasım 2020 ile 10 Nisan 2023 tarihleri arasındaki 600 günlük bir veri setinde gerçekleştirilmektedir. Veri seti, eğitim alt kümesi için %85 ve doğrulama alt kümesi için %15 olmak üzere 85:15 veri bölünme oranıyla kullanılmıştır. Model eğitimi, Orthogonal Matching Pursuit (OMP) algoritması kullanılarak gerçekleştirilmiştir. Eğitim sonrasında model, daha önce görülmemiş verileri kullanarak tahminlerini doğrulamaktadır. Bu aşamadaki bulgular, modelin Aselsan hisse senedi fiyatlarındaki hareketleri öngörebilme ve güvenilir bir şekilde tahmin edebilme yeteneğinin güçlü olduğuna işaret etmektedir. Ayrıca model, kullanıcının karar sürecini anlamasına ve tahminlerin arkasındaki nedenleri görmesine yardımcı olan bir yorumlanabilirlik kapasitesine sahiptir.

Anahtar Kelimeler

• Yorumlanabilirlik
• Tahmin Gücü
• Hisse Fiyatı
• Makine Öğrenimi
• Teknoloji Endeksi

Kaynakça

1. Bondia, R., Ghosh, S., and Kanjilal, K. (2016). International Crude Oil Prices and the Stock Prices of Clean Energy and Technology Companies: Evidence from Non-Linear Cointegration Tests with Unknown Structural Breaks. Energy, 101, 558–565. https://doi.org/10.1016/j.energy.2016.02.031
2. Cai, T. T., and Wang, L. (2011). Orthogonal Matching Pursuit for Sparse Signal Recovery with Noise. IEEE Transactions on Information Theory, 57(7), 4680–4688. https://doi.org/10.1109/tit.2011.2146090
3. Camgöz, M. (2022). Temettü Veriminin BIST Hisse Senedi Fiyatlarını Tahmin Gücünün Nedensellik Testleriyle Analizi. İnsan ve Toplum Bilimleri Araştırmaları Dergisi. https://doi.org/10.15869/itobiad.1110269
4. Carvalho, D. V, Pereira, E. M., and Cardoso, J. S. (2019). Machine Learning Interpretability: A Survey on Methods and Metrics. Electronics. Https://Doi.Org/10.3390/Electronics8080832
5. Cheadle, C., Vawter, M. P., Freed, W. J., and Becker, K. G. (2003). Analysis Of Microarray Data Using Z Score Transformation. Journal Of Molecular Diagnostics. https://doi.org/10.1016/s1525-1578(10)60455-2
6. Chmielewski, L., Amin, R., Wannaphaschaiyong, A., and Zhu, X. (2020). Network Analysis of Technology Stocks Using Market Correlation. Proceedings - 11th IEEE International Conference on Knowledge Graph, ICKG 2020, 267–274. https://doi.org/10.1109/icbk50248.2020.00046
7. Curtis, A., Smith, T. M., Ziganshin, B. A., and Elefteriades, J. A. (2016). The Mystery of the Z-Score. Aorta. https://doi.org/10.12945/j.aorta.2016.16.014
8. Dhutti, K., and Bahra, R. (2014). Stock Price Movement of Information Technology Sector Through Technical Analysis.

9. Dongrey, N. S. (2022). Study Of Market Indicators Used for Technical Analysis. International Journal of Engineering and Management Research. https://doi.org/10.31033/ijemr.12.2.11
10. Fenton, T. R., and Sauve, R. (2007). Using The LMS Method To Calculate Z-Scores for The Fenton Preterm Infant Growth Chart. European Journal of Clinical Nutrition. https://doi.org/10.1038/sj.ejcn.1602667
11. Gharghori, P., See, Q., and Veeraraghavan, M. (2011). Difference Of Opinion and The Cross-Section of Equity Returns: Australian Evidence. Pacific-Basin Finance Journal. https://doi.org/10.1016/j.pacfin.2011.03.004
12. Gupta, V., Grover, G., and Arora, M. (2022). Trend In BMI Z-Score Among Private Schools’ Students in Delhi Using Multiple Imputation for Growth Curve Model. Epidemiology Biostatistics and Public Health. https://doi.org/10.2427/11836
13. Hasbrouck, J. (2003). Intraday Price Formation in US Equity Index Markets. The Journal of Finance. https://doi.org/10.1046/j.1540-6261.2003.00609.x
14. Jefferson, A., Woodhead, H. J., Fyfe, S., Briody, J., Bebbington, A., Strauss, B. J. G., Jacoby, P., and Leonard, H. (2011). Bone Mineral Content and Density in Rett Syndrome And Their Contributing Factors. Pediatric Research. https://doi.org/10.1203/pdr.0b013e31820b937d
15. Kassouri, Y., Kacou, K. Y. T., and Alola, A. A. (2021). Are Oil-Clean Energy and High Technology Stock Prices in the Same Straits? Bubbles Speculation and Time-Varying Perspectives. Energy, 232, 121021. https://doi.org/10.1016/j.energy.2021.121021
16. Kim, J. (2022). Market‐Wide Shocks and The Predictive Power for the Real Economy in The Korean Stock Market. Pacific Economic Review. https://doi.org/10.1111/1468-0106.12405
17. Kocaarslan, B., and Soytas, U. (2019). Dynamic Correlations Between Oil Prices and the Stock Prices of Clean Energy and Technology Firms: The Role of Reserve Currency (US Dollar). Energy Economics, 84, 104502. https://doi.org/10.1016/j.eneco.2019.104502
18. Kułaga, Z., Litwin, M., Tkaczyk, M., Różdżyńska, A., Barwicka, K., Grajda, A., Świąder, A., Gurzkowska, B., Napieralska, E., and Pan, H. (2010). The Height-, Weight-, And BMI-For-Age of Polish School-Aged Children and Adolescents Relative to International and Local Growth References. BMC Public Health. https://doi.org/10.1186/1471-2458-10-109
19. Ling, P. W. (2013). The Stock Price Forecasting Comparative Research of The Use of Fractal Theory At Taiwan Traditional Industry and Technology Industry. Applied Mechanics and Materials, 274, 53–56. https://doi.org/10.4028/www.scientific.net/amm.274.53
20. Liu, K. (2022). China’s Reform Spree In 2021: Common Prosperity and Others. Economic Papers A Journal of Applied Economics and Policy. Https://Doi.Org/10.1111/1759-3441.12365
21. Martinez-Millana, A., Hulst, J. M., Boon, M., Witters, P., Fernandez-Llatas, C., Asseiceira, I., Calvo-Lerma, J., Basagoiti, I., Boeck, K. D., and Ribes-Koninckx, C. (2018). Optimisation Of Children Z-Score Calculation Based on New Statistical Techniques. Plos One. https://doi.org/10.1371/journal.pone.0208362
22. Mcmillan, D. G. (2017). Predicting Firm Level Stock Returns: Implications for Asset Pricing and Economic Links. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.3035982
23. Mei, Z., and Grummer-Strawn, L. M. (2007). Standard Deviation of Anthropometric Z-Scores as a Data Quality Assessment Tool Using The 2006 WHO Growth Standards: A Cross Country Analysis. Bulletin of the World Health Organization. https://doi.org/10.2471/blt.06.034421
24. Nasreen, S., Tiwari, A. K., Eizaguirre, J. C., and Wohar, M. E. (2020). Dynamic Connectedness Between Oil Prices and Stock Returns of Clean Energy and Technology Companies. Journal Of Cleaner Production, 260, 121015.
25. Neely, C. J., Rapach, D. E., Tu, J., and Zhou, G. (2014). Forecasting The Equity Risk Premium: The Role of Technical Indicators. Management Science. https://doi.org/10.1287/mnsc.2013.1838
26. Oza, V., Thakkar, P., and Thakkar, P. (2022). A Dynamic Scenario‐Driven Technique for Stock Price Prediction and Trading. Journal Of Forecasting. https://doi.org/10.1002/for.2848
27. Ramos-Llordén, G., Vegas-Sánchez-Ferrero, G., Liao, C., Westin, C.-F., Setsompop, K., and Rathi, Y. (2020). SNR- Enhanced Diffusion MRI With Structure-Preserving Low-Rank Denoising in Reproducing Kernel Hilbert Spaces. https://doi.org/10.48550/arxiv.2009.06600
28. Sukmadilaga, C., Santoso, J. C., and Ghani, E. K. (2023). Can Accounting Value Relevance and Pricing Error Influence Stock Price of High-Technology Service Enterprises? Economies 2023, Vol. 11, Page 48, 11(2), 48. https://doi.org/10.3390/economies11020048
29. Turhan, T., and Aydemir, E. (2021). A Financial Ratio Analysis on BIST Information and Technology Index (XUTEK) Using AHP-Weighted Grey Relational Analysis. Düzce Üniversitesi Bilim ve Teknoloji Dergisi. https://doi.org/10.29130/dubited.1011252
30. Ürkmez, E. K., and Bölükbaşi, Ö. (2021). The Impact of Exchange Rates on Stock Prices for Turkey: An Asymmetric Non-Linear Cointegration Analysis. Marmara Üniversitesi İktisadi ve İdari Bilimler Dergisi. https://doi.org/10.14780/muiibd.960267
31. Vasantha, S., Dhanraj, V., and Varadharajan, R. (2012). Stock Price Movement Through Technical Analysis: Empirical Evidence from The Information Technology Sector. Indian Journal of Finance, 6(10), 4–17. https://indianjournalofmarketing.com/index.php/ijf/article/view/72388
32. Yahoo Finance. (N.D.). Yahoo Finance. Retrieved January 11, 2025, From Https://Finance.Yahoo.Com/
33. Yeoh, W. W. (2022). The Study on The Impact of Klse Market Index Towards the Stock Price Performance Among the Leading Technology Companies. Opsearch: American Journal of Open Research, 1(2), 1–7. https://doi.org/10.58811/opsearch.v1i2.11
34. Zhang, G., and Du, Z. (2017). Co-Movements Among the Stock Prices of New Energy, High-Technology and Fossil Fuel Companies in China. Energy, 135, 249–256. https://doi.org/10.1016/j.energy.2017.06.103