Analysis of deep neural networks for automobile insurance claim prediction

Aditya Rizki Saputro; Hendri Murfi; Siti Nurrohmah

doi:10.1007/978-981-32-9563-6_12

Analysis of deep neural networks for automobile insurance claim prediction

Aditya Rizki Saputro, Hendri Murfi, Siti Nurrohmah

Department of Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

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 language	English
Title of host publication	Data Mining and Big Data - 4th International Conference, DMBD 2019, Proceedings
Editors	Yuhui Shi, Ying Tan
Publisher	Springer Verlag
Pages	114-123
Number of pages	10
ISBN (Print)	9789813295629
DOIs	https://doi.org/10.1007/978-981-32-9563-6_12
Publication status	Published - 1 Jan 2019
Event	4th International Conference on Data Mining and Big Data, DMBD 2019 - Chiang Mai, Thailand Duration: 26 Jul 2019 → 30 Jul 2019

Publication series

Name	Communications in Computer and Information Science
Volume	1071
ISSN (Print)	1865-0929

Conference

Conference	4th International Conference on Data Mining and Big Data, DMBD 2019
Country/Territory	Thailand
City	Chiang Mai
Period	26/07/19 → 30/07/19

Keywords

Big data
Claim prediction
Deep learning
Deep neural network
Structured data

Access to Document

10.1007/978-981-32-9563-6_12

Cite this

Saputro, A. R., Murfi, H., & Nurrohmah, S. (2019). Analysis of deep neural networks for automobile insurance claim prediction. In Y. Shi, & Y. Tan (Eds.), Data Mining and Big Data - 4th International Conference, DMBD 2019, Proceedings (pp. 114-123). (Communications in Computer and Information Science; Vol. 1071). Springer Verlag. https://doi.org/10.1007/978-981-32-9563-6_12

@inproceedings{8aa2c26e0e314c53b4c1e78bf6648e5d,

title = "Analysis of deep neural networks for automobile insurance claim prediction",

abstract = "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.",

keywords = "Big data, Claim prediction, Deep learning, Deep neural network, Structured data",

author = "Saputro, {Aditya Rizki} and Hendri Murfi and Siti Nurrohmah",

note = "Funding Information: Acknowledgements. This work was supported by Universitas Indonesia under PIT 9 2019 grant. Any opinions, findings, and conclusions or recommendations are the authors{\textquoteright} and do not necessarily reflect those of the sponsor. Publisher Copyright: {\textcopyright} 2019, Springer Nature Singapore Pte Ltd.; 4th International Conference on Data Mining and Big Data, DMBD 2019 ; Conference date: 26-07-2019 Through 30-07-2019",

year = "2019",

month = jan,

day = "1",

doi = "10.1007/978-981-32-9563-6_12",

language = "English",

isbn = "9789813295629",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "114--123",

editor = "Yuhui Shi and Ying Tan",

booktitle = "Data Mining and Big Data - 4th International Conference, DMBD 2019, Proceedings",

address = "Germany",

}

Saputro, AR, Murfi, H & Nurrohmah, S 2019, Analysis of deep neural networks for automobile insurance claim prediction. in Y Shi & Y Tan (eds), Data Mining and Big Data - 4th International Conference, DMBD 2019, Proceedings. Communications in Computer and Information Science, vol. 1071, Springer Verlag, pp. 114-123, 4th International Conference on Data Mining and Big Data, DMBD 2019, Chiang Mai, Thailand, 26/07/19. https://doi.org/10.1007/978-981-32-9563-6_12

Analysis of deep neural networks for automobile insurance claim prediction. / Saputro, Aditya Rizki; Murfi, Hendri ; Nurrohmah, Siti.
Data Mining and Big Data - 4th International Conference, DMBD 2019, Proceedings. ed. / Yuhui Shi; Ying Tan. Springer Verlag, 2019. p. 114-123 (Communications in Computer and Information Science; Vol. 1071).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Analysis of deep neural networks for automobile insurance claim prediction

AU - Saputro, Aditya Rizki

AU - Murfi, Hendri

AU - Nurrohmah, Siti

N1 - Funding Information: Acknowledgements. This work was supported by Universitas Indonesia under PIT 9 2019 grant. Any opinions, findings, and conclusions or recommendations are the authors’ and do not necessarily reflect those of the sponsor. Publisher Copyright: © 2019, Springer Nature Singapore Pte Ltd.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

KW - Big data

KW - Claim prediction

KW - Deep learning

KW - Deep neural network

KW - Structured data

UR - http://www.scopus.com/inward/record.url?scp=85069986429&partnerID=8YFLogxK

U2 - 10.1007/978-981-32-9563-6_12

DO - 10.1007/978-981-32-9563-6_12

M3 - Conference contribution

AN - SCOPUS:85069986429

SN - 9789813295629

T3 - Communications in Computer and Information Science

SP - 114

EP - 123

BT - Data Mining and Big Data - 4th International Conference, DMBD 2019, Proceedings

A2 - Shi, Yuhui

A2 - Tan, Ying

PB - Springer Verlag

T2 - 4th International Conference on Data Mining and Big Data, DMBD 2019

Y2 - 26 July 2019 through 30 July 2019

ER -

Analysis of deep neural networks for automobile insurance claim prediction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this