A SECTORAL PERSPECTIVE ON FRONTRUNNERS AND INFORMATION CASCADES: CENTRAL AND ISOLATED CLEARING ANALYSIS USING ISOLATION FOREST

Yıl 2024, Cilt: 12 Sayı: Özel Sayı, 293 - 321, 31.12.2024

Ömür Saltık

https://doi.org/10.52122/nisantasisbd.1557322

Öz

This study analyzes the effects of information asymmetry, strategic trading behaviors, and speculative movements in markets by using the stock prices and clearing data of 448 companies listed on Borsa Istanbul between September 3, 2021, and April 9, 2024. Within the framework of the concepts of information cascade and frontrunner, this study examines the behaviors of central brokers and isolated brokers in the market, evaluating their sectoral impacts and their roles in investment returns. The aim of the study is to understand the effects of speculative trading activities by isolated brokers and the long-term investments of central brokers on market dynamics. Anomaly detection was conducted using the Isolation Forest algorithm, and the impact of these anomalies on market prices was analyzed. Additionally, the relationships between brokerage firms were investigated using network theory, and factors influencing the flow of information in the market were assessed. The findings indicate that both central and isolated brokers tend to pursue high return opportunities in sectors such as technology and energy, while central brokers adopt lower-risk investment strategies in more stable sectors. K-Means clustering analysis was employed to group returns across sectors, revealing that in certain sectors like the RaH sector, isolated brokers achieved significant gains, whereas in others, central brokers were more dominant. These analyses provide important insights into the effects of information asymmetry and speculative trading in financial markets.

Anahtar Kelimeler

Isolation Forest, Anomaly Detection, Information Cascade, Frontrunner, Investor Behavior

SEKTÖREL PERSPEKTİFTEN ÖNCÜLER VE BİLGİ KASKADLARI: İZOLASYON ORMANI İLE MERKEZİ VE YALITILMIŞ TAKAS ANALİZİ

Öz

Bu çalışma, Borsa İstanbul’da işlem gören 448 şirketin 03.09.2021-09.04.2024 itibariyle hisse senedi fiyat ve takas verilerini kullanarak, piyasalardaki bilgi asimetrisi, stratejik ticaret davranışları ve spekülatif hareketlerin etkilerini analiz etmektedir. Bilgi kaskadı ve öncüler kavramları çerçevesinde piyasadaki merkezi düğümler ile izole edilmiş düğümlerin davranışlarını inceleyen bu çalışma, bu aracı kurumların sektörel etkilerini ve yatırım getirileri üzerindeki rollerini değerlendirmektedir. Çalışmanın amacı, özellikle izole edilmiş aracı kurumların tarafından yapılan spekülatif alım-satım hareketlerinin ve merkezi düğümlerin/aracı kurumların uzun vadeli yatırımlarının piyasa dinamiklerine etkilerini anlamaktır. Isolation Forest algoritması ile anomali tespiti yapılmış, bu anomalilerin piyasa fiyatları üzerindeki etkileri analiz edilmiştir. Ayrıca, aracı kurumların birbirleriyle olan ilişkileri ağ teorisi kullanılarak incelenmiş ve piyasadaki bilgi akışını etkileyen faktörler değerlendirilmiştir. Bulgular, teknoloji ve enerji gibi sektörlerde hem merkezi hem de izole edilmiş aracı kurumların yüksek getiri fırsatlarına yöneldiğini, buna karşın daha istikrarlı sektörlerde merkezi aracı kurumların daha düşük riskle yatırım yaptığını göstermektedir. K-Means kümeleme analizi ile sektörlerdeki getiriler gruplandırılmış ve restaurant ve otel sektörü gibi bazı sektörlerde izole edilmiş aracı kurumların önemli kazançlar elde ederken, diğer sektörlerde merkezi aracı kurumların daha baskın olduğu tespit edilmiştir. Bu analizler, finansal piyasalardaki bilgi asimetrisi ve spekülatif ticaretin etkilerini anlamada önemli bulgular sunmaktadır.

Anahtar Kelimeler

: Isolation Forest, Anomali Tespiti, Bilgi Çağlayanı, Öncüller, Yatırımcı Davranışları

Kaynakça

• Banerjee, A. V., (1992). "A Simple Model of Herd Behavior", The Quarterly Journal of Economics, 107(3), 797-817.
• Bikhchandani, S., Hirshleifer, D., & Welch, I., (1992). "A Theory of Fads, Fashion, Custom, and Cultural Change as Informational Cascades", Journal of Political Economy, 100(5), 992-1026.
• Breunig, M. M., Kriegel, H. P., Ng, R. T., & Sander, J., (2000, May). “LOF: Identifying Density-Based Local Outliers”, In Proceedings of the 2000 ACM SIGMOD international conference on Management of data 93-104).
• Cipriani, M., & Guarino, A., (2014). “Estimating a Structural Model of Herd Behavior in Financial Markets”, The American Economic Review, 104(1), 224-251.
• Delafuente, H. N., Astudillo, C. A., & Díaz, D., (2024). “Ensemble Approach Using k-Partitioned Isolation Forests for the Detection of Stock Market Manipulation”. Mathematics, 12(9), 1336.
• Doherty, O., (2018). “Informational Cascades In Financial Markets: Review And Synthesis”. Review of Behavioral Finance, 10(1), 53-69.
• Ester, M., Kriegel, H. P., Sander, J., & Xu, X., (1996, August). “A Density-Based Algorithm For Discovering Clusters In Large Spatial Databases With Noise”, In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, (34), 226-231.
• Fama, E. F., (1970). “Efficient capital markets”, Journal of Finance, 25(2), 383-417.
• Fiore, A., & Morone, A., (2008). “A Simple Note on Informational Cascades”, Economics, 2(1), 1.
• Froot, K. A., Scharfstein, D. S., & Stein, J. C., (1992). “Herd On The Street: Informational Inefficiencies In A Market With Short‐Term Speculation”, The Journal of Finance, 47(4), 1461-1484.
• Hirshleifer, D., & Teoh, S. H., (2003). “Herd Behavior and Cascading in Capital Markets: A Review and Synthesis”, European Financial Management, 9(1), 25-66.
• Huberman, G., & Regev, T. (2001). “Contagious Speculation and a Cure for Cancer: A Nonevent That Made Stock Prices Soar”, The Journal of Finance, 56(1), 387-396.
• Johnston, R., & Lachance, S., (2022). “The predictable campaign: Theory and evidence”, Electoral Studies, 75:102432.
• Kumar, A., & Lee, C. M., (2006). “Retail Investor Sentiment and Return Comovements”. The Journal of Finance, 61(6), 2451-2486.
• Liu, F. T., Ting, K. M., & Zhou, Z. H., (2008, December). “Isolation Forest”, In 2008 Eighth Ieee International Conference On Data Mining, 413-422.
• Raafat, R. M., Chater, N., & Frith, C., (2009). “Herding In Humans”. Trends In Cognitive Sciences, 13(10), 420-428.
• Scharfstein, D. S., & Stein, J. C., (1990). "Herd Behavior and Investment" The American Economic Review, 80(3), 465-479.
• Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C., (2001). “Estimating the Support of a High-Dimensional Distribution”. Neural Computation, 13(7), 1443-1471.
• Söderström, V., & Knudsen, K., (2022). Interpretable Outlier Detection in Financial Data: Implementation of Isolation Forest and Model-Specific Feature Importance, (Yayınlanmış) Yüksek Lisans Tezi. Uppsala Universitet Teknisk-Naturvetenskapliga Fakulteten.
• Ounacer, S., El Bour, H. A., Oubrahim, Y., Ghoumari, M. Y., & Azzouazi, M., (2018). “Using Isolation Forest In Anomaly Detection: The Case Of Credit Card Transactions”, Periodicals of Engineering and Natural Sciences, 6(2), 394-400.
• Tang, P. L., Le Pham, T. D., & Dinh, T. B., (2022, September). “Tree-Based Credit Card Fraud Detection Using Isolation Forest, Spectral Residual, and Knowledge Graph”, In International Conference on Machine Learning, Optimization, and Data Science (pp. 326-340). Cham: Springer Nature Switzerland.
• Tiniç, M., Iqbal, M. S., & Mahmud, S. F., (2020). “Information Cascades, Short-Selling Constraints, And Herding In Equity Markets”, Borsa Istanbul Review, 20(4), 347-357.
• Vijayakumar, V., Divya, N. S., Sarojini, P., & Sonika, K., (2020). “Isolation forest and local outlier factor for credit card fraud detection system”, International Journal of Engineering and Advanced Technology, 9, 261-265.
• Yang, Z., Li, H., Yang, X., Peng, H., Shi, J., Peng, M., ... & Bai, H. (2023, May). “User Log Anomaly Detection System Based on Isolation Forest”. In 2023 2nd International Joint Conference on Information and Communication Engineering, 79-84.