AI framework identifies suspicious trading patterns using K-Means++ clustering

Researchers have developed a new toolkit using K-Means++ clustering to detect suspicious trading patterns in capital markets. The framework analyzes a dataset of approximately one million financial transactions from 2012 to 2024, identifying 2.02% of trades as potentially fraudulent. The identified suspicious trades are categorized into types such as spoofing, pump and dump, insider trading, and fake breakouts, with a significant portion remaining unclassified due to the absence of ground truth data. The model's effectiveness is validated by a Silhouette Score of 0.561. AI

IMPACT Provides a novel AI-driven approach for detecting financial market manipulation, potentially improving market integrity.

RANK_REASON Academic paper detailing a new AI-driven framework for financial fraud detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• K-Means++
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →