Analysis of deep neural networks for automobile insurance claim prediction

Aditya Rizki Saputro, Hendri Murfi, Siti Nurrohmah

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)


Claim prediction is an important process in an automobile insurance industry to prepare the right type of insurance policy for each potential policyholder. The volume of available data to construct the model of the claim prediction is usually large. Nowadays, deep neural networks (DNN) becomes more popular in the machine learning field especially for unstructured data likes image, text, or signal. The DNN model integrates the feature selection into the model in the form of some additional hidden layers. Moreover, DNN is suitable for the large volume of data because of its incremental learning. In this paper, we apply and analyze the accuracy of DNN for the problem of claim prediction which has structured data. First, we show the sensitivity of the hyperparameters on the accuracy of DNN and compare the performance of DNN with standard neural networks. Our simulation shows that the accuracy of DNN is slightly better than the standard neural networks in term of normalized Gini.

Original languageEnglish
Title of host publicationData Mining and Big Data - 4th International Conference, DMBD 2019, Proceedings
EditorsYuhui Shi, Ying Tan
PublisherSpringer Verlag
Number of pages10
ISBN (Print)9789813295629
Publication statusPublished - 1 Jan 2019
Event4th International Conference on Data Mining and Big Data, DMBD 2019 - Chiang Mai, Thailand
Duration: 26 Jul 201930 Jul 2019

Publication series

NameCommunications in Computer and Information Science
ISSN (Print)1865-0929


Conference4th International Conference on Data Mining and Big Data, DMBD 2019
CityChiang Mai


  • Big data
  • Claim prediction
  • Deep learning
  • Deep neural network
  • Structured data


Dive into the research topics of 'Analysis of deep neural networks for automobile insurance claim prediction'. Together they form a unique fingerprint.

Cite this