Statistical matching for anomaly detection in insurance assets granular reporting

Abstract

Since 2016, insurance corporations report granular asset data in Solvency II templates on a quarterly basis. Assets are uniquely identified by codes that are required to be kept stable and consistent over time; nevertheless, due to reporting errors, unexpected changes in the codes may occur, causing inconsistencies when compiling insurance statistics. The paper addresses this issue as a statistical matching problem and a supervised classification approach is proposed to detect such anomalies. Test results show the potential benefits of machine learning techniques on data quality management processes and the efficiency gains arising from automation, especially during situations of constraints on human resources, as the ongoing pandemic.