Volume 22, Issue 2 (9-2025)
JSDP 2025, 22(2): 31-42 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Shaeeri Z, Kazemitabar J, Haghverdi S. Stock Market Anomaly Detection Using Behavioral Analysis. JSDP 2025; 22 (2) : 2
URL: http://jsdp.rcisp.ac.ir/article-1-1203-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1203-en.html
Associate Professor, Department of Electrical and Computer Engineering, Babol Noshirvani University of Technology, Babol, Iran
Abstract: (376 Views)
Stock market fraud, particularly front-running, is a deceptive practice in which traders exploit prior knowledge of significant orders placed by others to profit from stock price movements. Front-running is considered illegal because it involves using confidential or non-public information to manipulate the market for personal gain. This paper tries ti propose a novel, unsupervised, and real-time anomaly detection method based on behavioral analysis, specifically designed to identify front-running fraud within stock market transactions. The method focuses on building individual behavioral profiles for each trader, capturing their specific traits and patterns in stock buying and selling. These profiles serve as baselines for what is considered as 'normal' trading behavior for each trader.
To detect anomalies, we introduce a statistical framework where the risk of each transaction will be calculated by evaluating the deviation from the expected behavior based on the trader's historical actions. This deviation is a measure of how unusual the current transaction is in comparison to the trader’s typical actions. The risk calculation involves the use of the log-likelihood ratio, a concept derived from detection theory, which compares the likelihood of a transaction being normal or fraudulent. The conditional probability of a transaction being either fraudulent or non-fraudulent is computed, and the ratio of these probabilities has been taken on a logarithmic scale to define the transaction risk. This risk metric is then utilized to flag potentially suspicious behavior for further investigations.
Bayesian probability theory underpins the model, specifically employing Bayes' rule to update the likelihood of fraud as more data will be accumulated over time. The model assumes the independence of risk components, which simplifies the complexity of the system and improves computational efficiency. Despite the potential limitation of assuming independence, empirical studies have shown that this assumption often yields reliable results for detecting anomalous behavior, making the approach both practical and effective.
Behavioral profiling plays a key role in this method. By observing the individual’s trading history—such as the frequency, timing, and amounts of trades—the system learns a trader’s typical behavior. This behavioral information is critical because it accounts for the natural variance in a trader's actions over time, allowing the model to distinguish between normal fluctuations and abnormal activities that might indicate fraud. Key behavioral indicators include the timing of trades, the volume of trades, the frequency of transactions with specific counterparties, and the trader’s overall market engagement. Traders whose actions significantly deviate from their established patterns—such as purchasing large quantities of stocks at unusual times or interacting with the same trader excessively—are flagged as high-risk.
The simulation section of the paper uses 16 months of stock market transaction data, where features such as transaction amounts, time of trade, urgency, and consistency in trading with particular traders are analyzed to calculate the risk profile. The system ranks traders based on the risk scores of their transactions, enabling the detection of front-running activities in near real-time.
The results from the simulation indicate that the proposed method is highly effective in identifying front-running fraud. The use of behavioral profiling ensures that the system is adaptive to individual trading patterns, making it resistant to the evolving nature of fraud in financial markets. The methodology also provides a significant advantage over traditional rule-based systems, which often struggle to adapt to new fraud techniques as they emerge. Furthermore, this approach can be applied in live trading environments, making it a practical tool for regulatory bodies and market surveillance.
This paper contributes to the growing field of financial fraud detection by introducing an innovative approach that combines behavioral analysis with advanced statistical techniques. The findings underline the importance of real-time monitoring and adaptive fraud detection systems in maintaining market integrity. In the simulation section, stock market data of 16 months is used. Features related to amounts, hours, urgency, and trading with one trader in buying/selling have been used to obtain the ranking. Results show that the proposed method is effective in detecting front running cases
To detect anomalies, we introduce a statistical framework where the risk of each transaction will be calculated by evaluating the deviation from the expected behavior based on the trader's historical actions. This deviation is a measure of how unusual the current transaction is in comparison to the trader’s typical actions. The risk calculation involves the use of the log-likelihood ratio, a concept derived from detection theory, which compares the likelihood of a transaction being normal or fraudulent. The conditional probability of a transaction being either fraudulent or non-fraudulent is computed, and the ratio of these probabilities has been taken on a logarithmic scale to define the transaction risk. This risk metric is then utilized to flag potentially suspicious behavior for further investigations.
Bayesian probability theory underpins the model, specifically employing Bayes' rule to update the likelihood of fraud as more data will be accumulated over time. The model assumes the independence of risk components, which simplifies the complexity of the system and improves computational efficiency. Despite the potential limitation of assuming independence, empirical studies have shown that this assumption often yields reliable results for detecting anomalous behavior, making the approach both practical and effective.
Behavioral profiling plays a key role in this method. By observing the individual’s trading history—such as the frequency, timing, and amounts of trades—the system learns a trader’s typical behavior. This behavioral information is critical because it accounts for the natural variance in a trader's actions over time, allowing the model to distinguish between normal fluctuations and abnormal activities that might indicate fraud. Key behavioral indicators include the timing of trades, the volume of trades, the frequency of transactions with specific counterparties, and the trader’s overall market engagement. Traders whose actions significantly deviate from their established patterns—such as purchasing large quantities of stocks at unusual times or interacting with the same trader excessively—are flagged as high-risk.
The simulation section of the paper uses 16 months of stock market transaction data, where features such as transaction amounts, time of trade, urgency, and consistency in trading with particular traders are analyzed to calculate the risk profile. The system ranks traders based on the risk scores of their transactions, enabling the detection of front-running activities in near real-time.
The results from the simulation indicate that the proposed method is highly effective in identifying front-running fraud. The use of behavioral profiling ensures that the system is adaptive to individual trading patterns, making it resistant to the evolving nature of fraud in financial markets. The methodology also provides a significant advantage over traditional rule-based systems, which often struggle to adapt to new fraud techniques as they emerge. Furthermore, this approach can be applied in live trading environments, making it a practical tool for regulatory bodies and market surveillance.
This paper contributes to the growing field of financial fraud detection by introducing an innovative approach that combines behavioral analysis with advanced statistical techniques. The findings underline the importance of real-time monitoring and adaptive fraud detection systems in maintaining market integrity. In the simulation section, stock market data of 16 months is used. Features related to amounts, hours, urgency, and trading with one trader in buying/selling have been used to obtain the ranking. Results show that the proposed method is effective in detecting front running cases
Article number: 2
Keywords: Stock market fraud detection, behavioral profiling, data analytics, Front running, log-likelihood, Bayes Rule, anomaly detection.
Type of Study: Research |
Subject:
Paper
Received: 2021/01/11 | Accepted: 2025/03/8 | Published: 2025/09/13 | ePublished: 2025/09/13
Received: 2021/01/11 | Accepted: 2025/03/8 | Published: 2025/09/13 | ePublished: 2025/09/13
References
1. World Bank Open Data, 2023, Available: [Online] https://data.worldbank.org.
2. K. Golmohammadi, O. R. Zaiane, and D. Diaz, "Detecting stock market manipulation using supervised learning algorithms", International Conference on Data Science and Advanced Analytics (DSAA), IEEE, 2014. [DOI:10.1109/DSAA.2014.7058109]
3. Aksenov, A., Grebenchshikova, E., Fayzrakhmanov, R. "Front-running Model in the Stock Market", ieeexplore, 2020. [DOI:10.1109/SUMMA50634.2020.9280575]
4. V. Azevedo, Ch. Hoegner, "Enhancing stock market anomalies with machine learning", Quantitative finance and accounting, vol. 60, pp. 195-230, 2023 [DOI:10.1007/s11156-022-01099-z]
5. W. Hilal, S. A. Gadsden, and J. Yawney, "Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances", Expert systems with applications, Elsevier, vol.193, pp. 1-34, 2022. [DOI:10.1016/j.eswa.2021.116429]
6. C. Poutre, D. Chetelat, M. Morales, "Deep unsupervised anomaly detection in high-frequency markets", The journal of finance and data science, vol. 10, pp. 1-18, 2024. [DOI:10.1016/j.jfds.2024.100129]
7. D. Y. Chiu, J. Y. Zhou, and Zh. Ch. Wang, "Appling artificial immune algorithm to explore the seasonal effect in the stock market", International Conference on Software Intelligence and Applications, 2014.
8. Y. Cao, Y. Li, S. Coleman, A. Belareche, and T. M. McGinniti, "Hidden Markov model with abnormal states for detecting stock price manipulation", IEEE International Conference on Systems, Man, and Cybernetics, 2013. [DOI:10.1109/SMC.2013.514]
9. Y. Cao, Y. Li, S. Coleman, A. Belareche, T. M. McGinniti, "Adaptive hidden Markov model with anomaly states for price manipulation detection", IEEE Transactions on Neural Networks and learning systems, vol. 26, pp. 318-330, 2015. [DOI:10.1109/TNNLS.2014.2315042] [PMID]
10. Imperva's Web Application Firewall data sheet. Available: https://www.imperva.com/docs/TB_Dynamic_Profilin g.pdf.
11. LightCyber and Check Point Advanced Threat Protection solution brief. Available: https://www.checkpoint.com/download/downloads/products/solution-brief/SB_LightCyber.pdf.
12. HP Unifies Network Security Detection to Identify, Contain and Neutralize Patient Zero Infections. Available: http://www.hp.com/hpinfo/ newsroom/press_kits/2014/HPProtect2014/HPTippingPoint_Advisory.pdf.
13. Finding Advanced Threats Before They Strike: A Review of Damballa Failsafe Advanced Threat Protection and Containment. Available :http://www.sans.org/reading-room/whitepapers/analyst/finding-advanced-threats-strike-review-damballa-failsafe-advanced-threat-protecti-34705.
14. کاظمی تبار، سیدجواد، شهباززاده، مجید، «کشف تقلب در بازار بورس اوراق بهادار با استفاده از کاربرد نامساوی چبیشف»، فصلنامة پردازش علائم و دادهها، دورة 17، شمارة 1، صص 3-14، 1399.
14. S. J. Kazemitabar, M. Shahbazzadeh, "Stock market fraud detection, a probabilistic approach", Signal and data processing, vol. 17, no. 6, 2020. [DOI:10.29252/jsdp.17.1.3]
15. Y. Kim, S. Y. Sohn, "Stock fraud detection using peer group analysis", Expert Systems with Applications, pp. 8986-8992, 2012. [DOI:10.1016/j.eswa.2012.02.025]
16. B. Baesense, et al, "Fraud analytics using descriptive, predictive, and social network techniques", Wiley, 2015. [DOI:10.1002/9781119146841]
17. V. Goldwasser, "Stock market manipulation and short selling", Centre of corporate law and securities regulation, Faculty of law, The University of Melborn, 1999.
18. International Organization of Securities Commissions (IOSC), 2023, Available: https://www.iosco.org.
19. S. S. Huebner, "The Stock Marke", Kessinger Publishing, 2006.
20. A. Franklin, and D. Gale, "Stock-Price Manipulation", Review of FinancialStudies, vol. 5, pp. 503-529, 1992. [DOI:10.1093/rfs/5.3.503]
21. H. Hamedinia, R.Raei, S. Bajalan, S. Rouhani, "Analysis of Stock Market Manipulation using Generative Adversarial Nets and Denoising Auto-Encode Model", Advances in Mathematical Finance and Applications, 7 (1), pp. 133-151, 2021.
22. Z. Shaeiri, S. J. Kazemitabar, "Fast unsupervised autimobile insurance fraud detection based on spectral ranking of anomalies", International Journal of Engineering, vol. 33, no. 7, pp. 1240-1248, 2020. [DOI:10.5829/ije.2020.33.07a.10]
23. Z. Shaeiri, S. J. Kazemitabar, Sh. Bijani, M. Talebi, "Behavior-Based online anomaly detection for a nationwide short message service", Journal of AI and data mining, vol. 7, no. 2, pp. 239-247, 2019.
24. J. D. Kirkland et.al., "The NASD regulation advanced detection system (ASD)", AI Magazine, vol. 20, 1999.
25. H. Goldberg et.al., "The ANSD securities observation, news analysis and regulation systems (SONAR)", American Association for Artificial Intelligence (AAAI), 2003.
26. K. Golmohammadi, O. R. Zaiane, "Data mining applications for fraud detection in securities market", Intelligence and Security Informatics Conference (EISIC), 2012. [DOI:10.1109/EISIC.2012.51]
27. A. Kr, S. Yadav, and Marpe Sora, "Fraud Detection in Financial Statements using Text Mining Methods: A Review", IOP conference series, 2021.
28. Z. Yi, et.al, "Fraud detection in capital markets: A novel machine learning approach", Epert Systems with Applications, Elsevier, vol. 231, 2023. [DOI:10.1016/j.eswa.2023.120760]
29. S. Kim, J. Hong, Y. Lee, "A GANs-Based Approach for Stock Price Anomaly Detection and Investment Risk Management", Fourth ACM international conference on AI in finance, pp. 1-9, 2023. [DOI:10.1145/3604237.3626892]
30. J. Neyman, and E. S. Pearson, "On the problem of the most efficient tests of statistical hypotheses", Phil. Trans., pp. 694-706, 1993.
31. S. Lin, and D. J. Costello, "Error Control Coding (2nd Edition)", Pearson, 2014.
32. S. Viaene, G. Dedene, and R. Derig, "Auto claim fraud detection using Bayesian learning neural networks", Expert systems with applications, vol. 29, no. 3, pp. 653-666, 2005. [DOI:10.1016/j.eswa.2005.04.030]
33. S. Viaene, R. Derrig, and G. Dedene, "A case study of applying boosting naive bayes to claim fraud diagnosis", IEEE Transactions on Knowledge and Data Engineering, vol. 16, no. 5, pp. 612-620, 2004. [DOI:10.1109/TKDE.2004.1277822]
34. S. Viaene, R. Derrig, B. Baesens, and G. Dedene, "A comparison of state-of-the- art classification techniques for expert automobile insurance claim fraud detection" The Journal of Risk and Insurance, vol. 69, no. 3, pp. 373-421, 2002. [DOI:10.1111/1539-6975.00023]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
