International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

Data Driven Approach to Improve Profitability in Vehicle Insurance Sector

Abstract

The insurance industry faces significant challenges, including fraudulent claims and customer churn, impacting profitability and sustainability. This research presents a comprehensive data-driven approach to increase profitability in the vehicle insurance sector. This research employs advanced methodologies for Cross sell prediction, Vehicle Insurance Claim Prediction Models, customer survival analysis, churn prediction, and fraud detection using Machine Learning and Deep Learning. By leveraging diverse data sets encompassing policy details, demographics, sentiment analysis, imagery, and historical claims, the study achieves predictive accuracy between 85% to 95%, and fraud detection rates of approximately 80% to 85%. The project introduces the transformative app, VEGO, benefiting both insurance companies and policyholders. Additionally, a rigorous survival analysis addresses critical questions on customer churn dynamics, demonstrating remarkable retention rates. Survival analysis techniques, including Kaplan-Meier Survival Curves, Log-Rank Test, and Cox-proportional hazard models, were employed to analyze customer retention rates over a 72-month period. These models provided valuable insights into risk factors and their cumulative impact on survival time in the insurance context. The research yields insights into risk factors and their collective impact on survival time, while introducing a conservative approach to estimating customer lifetime value. This endeavor enhances analytical foundations in vehicle insurance, ushering in a customer-centric industry landscape.

Country : Sri Lanka

1 Savindi Welikadaarachchi2 Mereesha Botheju3 Dinushi Ariyasena4 Viruni Fernando5 Anjalie Gamage6 Poojani Gunathilake

  1. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  2. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  3. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  4. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  5. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  6. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka

IRJIET, Volume 7, Issue 10, October 2023 pp. 333-343

doi.org/10.47001/IRJIET/2023.710045

Full Paper
Download

References

[1]

H. Z. a. P. Z. Y. Chen, Study of Customer Lifetime Value Model Based on Survival-Analysis Methods, pp. 266-270, 2009.

[2]

B. M. D. M. a. B. L. P. Datta, "Automated cellular modeling and prediction on a large scale"," vol. 14, pp. 485-502, 2000.

[3]

S. H. a. Y. L. J. Ahn, "Customer churn analysis: Churn determinants and mediation effects of partial defection in the korean mobile telecommunications service industry," vol. 30, pp. 552-568, 2006.

[4]

V. R. a. V. S. G. G. Sundarkumar, "One-class support vector machine based undersampling," pp. 1-7, 2015.

[5]

I. B. a. G. Toderean, "Churn prediction in the telecommunications sector using support vector machine," vol. 22, pp. 1-5, 2013.

[6]

L. Y. a. X. Guo-en, "he explanation of support vector machine in customer churn prediction," pp. 1-4, 2010.

[7]

K. C. a. D. V. d. Poel, "Churn prediction in subscription services: An application of support vector machines while comparing two parameter-selection techniques," vol. 34, pp. 313-327, 2008.

[8]

A. S. a. P. K. Panigrahi, "A neural network based approach for predicting customer churn in cellular network services," vol. 27, pp. 26-31, 2011.

[9]

Y. Y. L. C. a. S. Z. X. Hu, "Research on a customer churn combination prediction model based on decision tree and neural network," pp. 129-132, 2020.

[10]

S. B. a. S. Srivatsa, "Naive bayes classification approach for mining life insurance databases for effective prediction of customer p over life insurance products," vol. 51.

[11]

L. F. a. H. Wang, "Estimating insurance attrition using survival analysis", Casualty Actuarial Society," vol. 8, pp. 55-72, 2014.

[12]

D. V. d. P. a. B. Lariviere, "Customer attrition analysis for financial services using proportional hazard models," vol. 157, pp. 196-217.

[13]

T. L. O. Goonetilleke, "Mining life insurance data for customer attrition analysis," vol. 1, pp. 52-58.

[14]

K. C. a. Y. X. W. H Au, "A novel evolutionary data mining algorithms with applications to churn prediction," pp. 532-545.

[15]

V. S. a. D. K. Satpathi, "An Exploratory Study on the Use of Machine Learning Techniques in Insurance Industry".

[16]

G. D. O. O. a. S. Cai, "A hybrid churn prediction model in mobile telecommunication industry," vol. 4, pp. 55-62, 2014.

[17]

G. M. F. M. Qazi, "Predictive Modeling in Insurance: A Survey," vol. 50, pp. 68:1-68:36, 2018.

[18]

R. D. O. H. R. O. a. H. F. Amjad Hudaib, "Hybrid data mining models for predicting customer churn," vol. 8, pp. 91-96, 2015.

[19]

Y. X. X. L. a. W. Y. EWT Ngai, "Customer churn prediction using improved balanced random forests," vol. 36, pp. 5445-5449, 2008.

[20]

L. X. X. Y. a. J. E. Ying Weiyun, "Preventing customer churn by using random forests modeling," pp. 429-434, 2008.

[21]

M. B. a. S. Krummaker, "Prediction of claims in export credit finance: a comparison of four machine learning techniques," vol. 8, 2020.

[22]

L. I. a. S. Zeadally, "Healthcare Insurance Frauds: Taxonomy and Blockchain-Based Detection Framework (Block-HI)," vol. 23, pp. 36-43, 2021.

[23]

I. Matloob, "Sequence Mining and Prediction- Based Healthcare Fraud Detection Methodology," vol. 8, pp. 143256-143273, 2020.

[24]

E. Alamir, "Motor Insurance Claim Status Prediction using Machine Learning Techniques".

[25]

A. V. C. Team, "Applications of Machine Learning and AI in Insurance".

[26]

S. I. Inc, "Predictive Modeling with Imbalanced Data: An Application to Bank Telemarketing Response," 2018.

[27]

V. Ganganwar, "An Overview of Classification Algorithms for Imbalanced Datasets".

[28]

K. L. L. C.-Y. J. Peng, "An Introduction to Logistic Regression Analysis and Reporting," vol. . 96, pp. 12-23, 2002.

[29]

A. Usman, "Binary Logistic Regression Analysis on Admitting Students using JAMB Score".

[30]

T. R. a. C. Lo, "Determinants of User Acceptance of Internet Banking: An Empirical Study".

[31]

W. A. Kamakura, "Cross-Selling," www.researchgate.net, 2008.

[32]

P. P. A. Anit, "Modeling complex longitudinal consumer behavior with Dynamic Bayesian networks: An Acquisition Pattern Analysis application," ResearchGate.

[33]

G. M. F. M. Qazi, "Predictive modeling of insurance sales using multivariate adaptive regression splines," ACM SIGKDD Explorations Newsletter, vol. 18, pp. 22-32, 2016.

[34]

K. A. B. M. L. H. "Use of statistical models to predict feed intake of beef cattle," vol. 89, pp. 3181-3191, 2011.

[35]

"Introduction to Logistic Regression Analysis and Reporting," vol. 96, pp. 12- 16, 2002.

[36]

A. Usman, "Binary logistic regression analysis on ADDMITING students using jamb score".

[37]

K. L. L. C. J. Peng, "An Introduction to Logistic Regression Analysis and Reporting," vol. 96, p. 96, 2002.

[38]

A. Usman, "Binary logistic regression analysis on ADDMITING students using jambscore".

Copyright @ 2026-2017 IRJIET. All Right Reserved.

Developed by Byzero Technologies