Estimating The Stock Returns of Companies Exposed to Insider Trading with The K-Nearest Neighbor Algorithm: Example of USA Stock Markets

Abstract

In this study, the returns of the companies traded in the US Stock Markets and exposed to insider trading were estimated after 3, 9, 15, 21 and 27 months of the date of insider trading by using 10121 transaction data for the period 01.01.2020 - 26.02.2022. The results were estimated with KNN (K Nearest Neighbor Algorithm), one of the supervised data mining methods. As a result of the analysis, 224 of 257 samples exposed to trade in the period of 01.01.2022 - 26.03.2022 were estimated in the correct return range and the 3-months stock return estimation success was found to be 87.16%. In the period of 01.07.2021 to 31.12.2021, 1936 of 2358 samples exposed to trading were estimated in the right return range, and the 9-month stock return estimation success was determined to be 82.10%. 2495 of 2919 samples exposed to trade in the period of 01.01.2021 - 30.06.2021 were estimated in the correct return range and the 15-months stock return estimation success was found to be 85.47%. In the period of 01.07.2020 to 31.12.2020, 1980 of 2267 samples exposed to trading were estimated in the correct return range, and the 21-months stock return estimation success was determined to be 87.34%. Lastly, 2016 of 2320 samples exposed to trade in the period of 01.01.2020 - 30.06.2020 was estimated in the correct return range and the 27-months return estimation success was found to be 86.90%.

Keywords

• Insider Trading
• Stock Return Estimation
• K-Nearest Neighbor Algorithm
• USA Stock Markets

İçeriden Öğrenenlerin Ticaretine Maruz Kalan Şirketlere Ait Hisse Senedi Getirilerinin K-En Yakın Komşu Algoritması İle Tahmin Edilmesi: ABD Borsaları Örneği

Abstract

Bu çalışmada ABD Borsalarında işlem gören ve içeriden öğrenenlerin ticaretine maruz kalan şirketlere ait 01.01.2020-26.02.2022 dönemindeki 10121 işlem verileri alınarak ilgili şirketlerin içeriden öğrenenlerin ticareti tarihinden 3, 9, 15, 21 ve 27 ay sonraki getirileri tahmin edilmiştir. Sonuçlar denetimli veri madenciliği yöntemlerinden KNN (K En Yakın Komşu Algoritması) ile tahmin edilmiştir. Analiz sonucunda 01.01.2022-26.03.2022 döneminde ticarete maruz kalan 257 örneğin 224’ü doğru getiri aralığında tahmin edilmiş ve 3 ay öncesi hisse senedi getiri tahmin başarımı %87,16 olarak bulunmuştur. 01.07.2021-31.12.2021 döneminde ticarete maruz kalan 2358 örneğin 1936’sı doğru getiri aralığında tahmin edilmiş ve 9 ay öncesi hisse senedi getiri tahmin başarımı %82,10 olarak bulunmuştur. 01.01.2021-30.06.2021 döneminde ticarete maruz kalan 2919 örneğin 2495’i doğru getiri aralığında tahmin edilmiş ve 15 ay öncesi hisse senedi getiri tahmin başarımı %85,47 olarak bulunmuştur. 01.07.2020-31.12.2020 döneminde ticarete maruz kalan 2267 örneğin 1980’i doğru getiri aralığında tahmin edilmiş ve 21 ay öncesi hisse senedi getiri tahmin başarımı %87,34 olarak bulunmuştur. 01.01.2020-30.06.2020 döneminde ticarete maruz kalan 2320 örneğin 2016’sı doğru getiri aralığında tahmin edilmiş ve 27 ay öncesi getiri tahmin başarımı %86,90 olarak bulunmuştur.

Keywords

• İçeriden Öğrenenlerin Ticareti
• Hisse Senedi Getiri Tahmini
• K En yakın Komşu Algoritması
• ABD Borsaları

References

1. Adams, B.J., Perry, T. and Mahoney, C. (2018). The challenges of detection and enforcement of insider trading. Journal of Business Ethics, 153(2), 375-388 https://doi.org/10.1007/s10551-016-3403-4
2. Agrawal, A. and Nasser, T. (2012). Insider trading in takeover targets. Journal of Corporate Finance, 18(3), 598-625. https://doi.org/10.1016/j.jcorpfin.2012.02.006
3. Ambrose, J.M. and Seward, J.A. (1988). Best’s ratings, financial ratios and prior probabilities in insolvency prediction. The Journal of Risk and Insurance, 55(2), 229-244. https://doi.org/10.2307/253325
4. Arif, S., Kepler J., Schroeder, J. and Taylor, D. (2018). Audit process, private information, and insider trading. Review of Accounting Studies, Advance online publication. https://doi.org/10.1007/s11142-022-09689-x
5. Clacher, I., Hillier, D. and Lhaopadchan, S. (2009). Corporate insider trading: A literature review. Spanish Journal of Finance and Accounting, 38(143), 373-397. https://doi.org/10.1080/02102412.2009.10779670
6. Çelik, U., Akçetin, E. ve Gök, M. (2017). Rapidminer ile veri madenciliği (1. bs). Pusula Yayınları: İstanbul.
7. de Ferrieres, M. (2021a). Estimating the impact of a new generation of entrepreneurs as disruptive entrants in the insurance industry in Singapore (Unpublished doctoral dissertation). Horizon University, Paris.
8. de Ferrieres, M. (2021b). A literature review on digital disruption in the context of the insurance industry (Unpublished doctoral dissertation). Horizon University, Paris.

9. Dener, M., Dörterler, M. and Orman, A. (2009). Açık kaynak kodlu veri madenciliği programları: WEKA’da örnek uygulama. XI. Akademik Bilişim Konferansı’nda sunulan bildiri, Şanlıurfa. Erişim adresi: https://ab.org.tr/ab09/kitap/dener_dorterler_AB09.pdf
10. Donoho, S. (2004). Early detection of insider trading in option markets. In W. Kim and R. Kohavi (Eds.), Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (pp. 420-429). Papers presented at the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle: Association for Computing Machinery.
11. Enke, D. and Thawornwong, S. (2005). The use of data mining and neural networks for forecasting stock market returns. Expert Systems with Applications, 29, 927-940. https://doi.org/10.1016/j.eswa.2005.06.024
12. Esen, M.F., Bilgic, E. and Basdas, U. (2019). How to detect illegal corporate insider trading? A data mining approach for detecting suspicious insider transactions. Intelligent Systems in Accounting, Finance and Management, 26(2), 60-70. https://doi.org/10.1002/isaf.1446
13. Fischel, D.R. and Carlton, D.W. (1982). The regulation of insider trading. Stanford Law Review, 35, 857-895. https://doi.org/10.2307/1228706
14. Gestel, T.V., Martens, D., Baesens, B., Feremans, D., Huysmans, J. and Vanthienen, J. (2007). Forecasting and analyzing insurance companies’ ratings. International Journal of Forecasting, 23(3), 513-529. https://doi.org/10.1016/j.ijforecast.2007.05.001
15. Gupta, S. and Hossain, L. (2011). Towards near-real-time detection of insider trading behaviour through social networks. Computer Fraud & Security, 1, 7-16. https://doi.org/10.1016/S1361-3723(11)70006-9
16. Gurufocus. (2022). İçeriden öğrenenlerin ticareti verileri [Veri Seti]. Erişim adresi: https://www.gurufocus.com
17. Hazen, T.L. (2010). Identifying the duty prohibiting outsider trading on material nonpublic information. Hastings Law Journal, 61, 881-916. Retrieved from https://repository.uchastings.edu
18. Islam, S.R., Ghafoor, S.K. and Eberle, W. (2018). Mining illegal insider trading of stocks: A proactive approach. Paper presented at the 2018 IEEE International Conference on Big Data. Seattle, USA. Retrieved from https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8622303
19. Kılıç, S. (2015). Kappa testi. Journal of Mood Disorders, 5(3), 142-144. doi:10.5455/jmood.20150920115439
20. Kornilov, D.A. and Kornilova, E.V. (2020). Warren Buffett indicator and market correction. Development and Security in a Pandemic, 3, 54-62. Retrieved from https://ds.nntu.ru/
21. Liang, D., Tsai, C.F. and Wu, H.T. (2015). The effect of feature selection on financial distress prediction. Knowledge-Based Systems, 73, 289-297. https://doi.org/10.1016/j.knosys.2014.10.010
22. Liu, R., Mai, F., Shan, Z. and Wu, Y. (2020). Predicting shareholder litigation on insider trading from financial text: An interpretable deep learning approach. Information & Management, 57(8), 103387. https://doi.org/10.1016/j.im.2020.103387
23. Özdemir, A.K., Tolun, S. ve Demirci, E. (2011). Endeks getirisi yönünün ikili sınıflandırma yöntemiyle tahmin edilmesi: İMKB 100 endeksi örneği. Niğde Üniversitesi İİBF Dergisi, 4(2), 45-59. Erişim adresi: https://dergipark.org.tr/en/pub/niguiibfd/
24. Özkan, Y. (2016). Veri madenciliği yöntemleri (1. bs.). İstanbul: Papatya Yayınları.
25. Phua, C., Lee, V., Smith, K. and Gayler, R. (2010). A comprehensive survey of data mining-based fraud detection research. arXiv preprint arXiv:1009.6119. https://doi.org/10.48550/arXiv.1009.6119
26. Revina, D.S. (2018). The historic development of the stock market in Russia and its characteristics. PRO-Economics, 1, 1-5. Retrieved from https://en.proeconomics.ru/
27. Rodchenkov, M.V. (2021). Problems and specifics of the convergence of national accounting systems under the influence of IFRS. Bulletin of Moscow University, 4, 29-48. https://doi.org/10.38050/01300105202142
28. Silahtaroğlu, G. (2016). Veri madenciliği: Kavram ve algoritmaları. İstanbul: Papatya Yayıncılık Eğitim.
29. Stockl, T. and Palan, S. (2018). Catch me if you can. Can human observers identify insiders in asset markets? Journal of Economic Psychology, 67, 1-17. https://doi.org/10.1016/j.joep.2018.04.004
30. Wu, C.-C., Lin, B.-H. and Yang, T.-H. (2018). Insider trading and institutional holdings in mergers and acquisitions. Universal Journal of Accounting and Finance, 6(4), 144-155. doi:10.13189/ujaf.2019.060403