A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companies

This article proposes a hybrid model to assist insurance companies accurately assess the risk of increasing claims for their premiums. The model integrates long short-term memory (LSTM) networks and convolutional neural networks (CNN) to analyze historical claim data and identify emerging risk trend...

Full description

Saved in:
Bibliographic Details
Main Authors: Walaa Gamaleldin, Osama Attayyib, Mrim M. Alnfiai, Faiz Abdullah Alotaibi, Ruixing Ming
Format: Article
Language:English
Published: PeerJ Inc. 2025-04-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2830.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850201047909269504
author Walaa Gamaleldin
Osama Attayyib
Mrim M. Alnfiai
Faiz Abdullah Alotaibi
Ruixing Ming
author_facet Walaa Gamaleldin
Osama Attayyib
Mrim M. Alnfiai
Faiz Abdullah Alotaibi
Ruixing Ming
author_sort Walaa Gamaleldin
collection DOAJ
description This article proposes a hybrid model to assist insurance companies accurately assess the risk of increasing claims for their premiums. The model integrates long short-term memory (LSTM) networks and convolutional neural networks (CNN) to analyze historical claim data and identify emerging risk trends. We analyzed data obtained from insurance companies and found that the hybrid CNN-LSTM model outperforms standalone models in accurately assessing and categorizing risk levels. The proposed CNN-LSTM model achieved an accuracy of 98.5%, outperforming the standalone CNN (95.8%) and LSTM (92.6%). We implemented 10-fold cross-validation to ensure robustness, confirming consistent performance across different data splits. Furthermore, we validated the model on an external dataset to assess its generalizability. The results demonstrate that the model effectively classifies insurance risks in different market environments, highlighting its potential for real-world applications. Our study contributes to the insurance industry by providing valuable insights for effective risk management strategies and highlights the model’s broader applicability in global insurance markets.
format Article
id doaj-art-adeec18bb9b349a994ec18c055dbe25e
institution OA Journals
issn 2376-5992
language English
publishDate 2025-04-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-adeec18bb9b349a994ec18c055dbe25e2025-08-20T02:12:07ZengPeerJ Inc.PeerJ Computer Science2376-59922025-04-0111e283010.7717/peerj-cs.2830A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companiesWalaa Gamaleldin0Osama Attayyib1Mrim M. Alnfiai2Faiz Abdullah Alotaibi3Ruixing Ming4School of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, ChinaSchool of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, ChinaDepartment of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi ArabiaDepartment of Information Science, College of Humanities and Social Sciences, King Saud University, Riyadh, Saudi ArabiaSchool of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, ChinaThis article proposes a hybrid model to assist insurance companies accurately assess the risk of increasing claims for their premiums. The model integrates long short-term memory (LSTM) networks and convolutional neural networks (CNN) to analyze historical claim data and identify emerging risk trends. We analyzed data obtained from insurance companies and found that the hybrid CNN-LSTM model outperforms standalone models in accurately assessing and categorizing risk levels. The proposed CNN-LSTM model achieved an accuracy of 98.5%, outperforming the standalone CNN (95.8%) and LSTM (92.6%). We implemented 10-fold cross-validation to ensure robustness, confirming consistent performance across different data splits. Furthermore, we validated the model on an external dataset to assess its generalizability. The results demonstrate that the model effectively classifies insurance risks in different market environments, highlighting its potential for real-world applications. Our study contributes to the insurance industry by providing valuable insights for effective risk management strategies and highlights the model’s broader applicability in global insurance markets.https://peerj.com/articles/cs-2830.pdfMachine learningDeep learningCNN-LSTMClaimsPremiumsMeasuring risk
spellingShingle Walaa Gamaleldin
Osama Attayyib
Mrim M. Alnfiai
Faiz Abdullah Alotaibi
Ruixing Ming
A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companies
PeerJ Computer Science
Machine learning
Deep learning
CNN-LSTM
Claims
Premiums
Measuring risk
title A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companies
title_full A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companies
title_fullStr A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companies
title_full_unstemmed A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companies
title_short A hybrid model based on CNN-LSTM for assessing the risk of increasing claims in insurance companies
title_sort hybrid model based on cnn lstm for assessing the risk of increasing claims in insurance companies
topic Machine learning
Deep learning
CNN-LSTM
Claims
Premiums
Measuring risk
url https://peerj.com/articles/cs-2830.pdf
work_keys_str_mv AT walaagamaleldin ahybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT osamaattayyib ahybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT mrimmalnfiai ahybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT faizabdullahalotaibi ahybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT ruixingming ahybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT walaagamaleldin hybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT osamaattayyib hybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT mrimmalnfiai hybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT faizabdullahalotaibi hybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies
AT ruixingming hybridmodelbasedoncnnlstmforassessingtheriskofincreasingclaimsininsurancecompanies