Articles from Cass Knowledge

Prediction of claims in export credit finance - a comparison of four machine learning techniques

This study investigates machine learning techniques for claims prediction using an international dataset on export credit insurance claims.

Predicting claims is a critical challenge for insurers. Changes in expected claims not only affect the capital of an insurer, but also its capacity to underwrite further business. Insurance companies can increase premium rates and adjust their underwriting policy to balance the effect of unexpected claims but this has a negative impact on business opportunities. Therefore, accuracy of prediction is hugely important.

This study evaluates four machine learning techniques (Decision Trees, Random Forests, Neural Networks, and Probabilistic Neural Networks) on their ability to accurately predict export credit insurance claims. Export credit insurance is a tool for exporters in mitigating risks that arise from exporting to other countries. It covers companies against the risk of non-payment of their buyer due to commercial and political risks. Often, lenders are only willing to grant financing if export credit insurance is provided. Therefore, export credit insurance is regularly a key requirement for the realisation of an export transaction.

The researchers conducted a comparative study of the four techniques and evaluated their ability to accurately predict claims based on a unique dataset of export credit insurance claims over the period of 2005 to 2018. Furthermore, they compared the techniques against the performance of a simple heuristic, based on moving averages of claims from destinations that the insurer has done business with previously. The analysis is based on the utilisation of a dataset provided by the Berne Union, which is the most comprehensive collection of export credit insurance data and has been used in only two scientific studies so far.

All of the machine learning techniques performed relatively well in predicting whether or not claims would be incurred, and, with limitations, in predicting the order of magnitude of the claims. No satisfactory results were achieved predicting actual claim ratios, however. Random Forests performed significantly better than the others against all prediction tasks, and most reliably carried their validation performance forward to test performance.

The paper Prediction of claims in export credit finance: a comparison of four machine learning techniques can be downloaded at City Research Online. It has been published in Risks.