Regularization learning network for insurance claim prediction in travel insurance

Jacob Teofilus Gamaliel, Hendri Murfi

Research output: Contribution to journalArticlepeer-review

Abstract

Insurance is a service provided by an insurance company to ensure the risk of financial loss to a person or group that pays a premium based on the agreement. One of the insurance products is travel insurance, which services to divert the risk of financial loss due to accidents in transit. The insurance company must be able to do the right analysis to predict whether a premium payer will file a claim or not in the future, in order to minimize losses suffered by the company. From the machine learning point of view, the problem of claim prediction is a classification problem. Deep Neural Networks (DNN) is one of the recent machine learning methods to solve the claim prediction problem. However, DNN did not provide better accuracy than the standard neural networks (NN). In this paper, regularization Learning Networks (RLN) is used for claim prediction in travel insurance. Our simulations show that RLN improves the performance of DNN and gives better accuracy than both DNN and NN.

Original languageEnglish
Pages (from-to)1496-1503
Number of pages8
JournalJournal of Advanced Research in Dynamical and Control Systems
Volume12
Issue number4 Special Issue
DOIs
Publication statusPublished - 1 Jan 2020

Keywords

  • Claim Prediction
  • Deep Neural Network
  • Regularization Learning Network
  • Tabular Data
  • Travel Insurance

Fingerprint Dive into the research topics of 'Regularization learning network for insurance claim prediction in travel insurance'. Together they form a unique fingerprint.

Cite this