Statistical matching for anomaly detection in insurance assets granular reporting

Vittoria La Serra and Emiliano Svezia

No 22, IFC Working Papers from Bank for International Settlements

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.

Keywords: data quality management; insurance data; machine learning; record linkage; statistical matching (search for similar items in EconPapers)
JEL-codes: C18 C81 G22 (search for similar items in EconPapers)
Pages: 14 pages
Date: 2022-10
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.bis.org/ifc/publ/ifcwork22.pdf Full PDF document (application/pdf)
https://www.bis.org/ifc/publ/ifcwork22.htm (text/html)

Related works:
Chapter: Statistical matching for anomaly detection in insurance assets granular reporting (2023)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bis:bisiwp:22

Access Statistics for this paper

More papers in IFC Working Papers from Bank for International Settlements Contact information at EDIRC.
Bibliographic data for series maintained by Martin Fessler ().