An Individual Claims Reserving Model for Reported Claims
28 Pages Posted: 22 Jun 2020
Date Written: May 28, 2020
Abstract
We present a claims reserving technique that uses claim-specific feature and past payment information in order to estimate claims reserves for individual reported claims. We design one single neural network allowing us to estimate expected future cash flows for every individual reported claim. We introduce a consistent way of using dropout layers in order to fit the neural network to the incomplete time series of past individual claims payments. A proof of concept is provided by applying this model to a data set for which the true outstanding payments for reported claims are known.
Keywords: Claims Reserving, Individual Claims, RBNS Reserves, Neural Networks, Multi-Task Learning, Dropout, Time Series, Micro Reserving
JEL Classification: G22, C02, C13, C15, C45, C50, C51, C52, C53
Suggested Citation: Suggested Citation