نویسنده
دانشگاه علم و صنعت، تهران، ایران.
کلیدواژهها
عنوان مقاله English
نویسنده English
Purpose: The objective of this research is to present a comprehensive framework for identifying anomalies in Commitments of Traders (COT) report data and to investigate their role in detecting economic trends, market disruptions, and sudden changes.
Methodology: In this study, after preprocessing the COT data, statistical methods including Z-score and Interquartile Range (IQR) were combined with machine learning algorithms, including Isolation Forest and One-Class Support Vector Machine (OC-SVM). Subsequently, by creating aggregated anomaly indicators, the points that were identified as anomalies by all methods were extracted
Findings: The results showed that the identified anomalies have a significant relationship with major economic events, including the 2008 global financial crisis and the COVID-19 pandemic in 2020. Furthermore, the proposed hybrid method, by reducing false positives, generated a high-confidence anomaly set consisting of 1,638 anomaly points.
Originality/Value: This research, by integrating statistical methods, machine learning, and Manifold Learning, provides an accurate and reliable framework for analyzing complex financial market data and creates the foundation for developing interactive dashboards for real-time market monitoring.
کلیدواژهها English
