Abstract:
An unsupervised machine learning model that uses the mechanism of the Local Outlier Factor to flag and detect
ambiguous and potentially fraudulent claims in Accidental and Healthcare insurance is proposed. The ethos of this model is to
comprehensively automate and expedite the claim investigation process using certain parameters to aid the claim appraiser’s
workload of going through straightforward claims and saving their time to investigate more critical and complex claims. The model
flags claims which are anomalous which when compared to the model’s threshold and input parameters are generated as alerts. These
alerts generated are then investigated for fraud based on the parameters stated. The model can classify these claims and the cost of
billable associated with these claims by reporting an accuracy of 99.5% for the Local Outlier Factor model in comparison with other
implemented techniques of Isolation Forest which had an accuracy of only 78.37%. The clusters were visualised with DBSCAN
using Plotly whereas the outliers were seen using TSNE. Our model has been tested and validated on real-world data and is showing
promising results. Being able to identify and flag potentially fraudulent claims before they are paid out can save insurance companies
a lot of money and resources. The model can classify the claims based on risk levels and associated costs. This will help the
insurance company prioritise which claims to investigate first and allocate their resources accordingly. Our model has been tested
and validated on real-world data and is showing promising results. Being able to identify and flag potentially fraudulent claims
before they are paid out can save insurance companies a lot of money and resources. The model can classify the claims based on risk
levels and associated costs. This will help the insurance company prioritise which claims to investigate first and allocate their
resources accordingly.
