An Analytical Approach to Predict Auto Insurance Claim using Machine Learning Techniques


Authors : Heena Kouser; Hemanth Kumar

Volume/Issue : Volume 9 - 2024, Issue 7 - July

Google Scholar : https://tinyurl.com/msn8zntk

Scribd : https://tinyurl.com/ytfkbdh9

DOI : https://doi.org/10.38124/ijisrt/IJISRT24JUL1269

Abstract : Machine Learning business is regular in the insurance market to enhance the efficiency and predictive skills of the insurance industry linear regression as an initial and effective ml method is adopted in this work predicting automobile insurance claim is undertaken using these large datasets which provides the detailed driver characteristics vehicle characteristics and historical claim insights becomes possible to apply linear regression analyses to indicate and predict the likelihood and frequency of upcoming claims to insurers One of the primary motivations for linear regression is a very easy tool has it is pretty simple to use, easy to interpret and at the same time easy to scale it can benefit in managing and resolve the premium pricing and improvement of risk assessment along with the enhancement of the financial stability while applying linear regression the study explains how it can be utilized in auto insurance claims prediction the potential idea of using better ml models for more investigation and its pros and cons this model is mainly assessed in line with its predictive accuracy utilizing metrics reminiscent of mse and r-squared (R2).

Keywords : Machine Learning Techniques; Prediction Model; Auto Insurance Claim.

References :

  1. N. Patel and M. Trivedi, "Deep Learning for Auto Insurance Claim Prediction." Insurance: Mathematics and Economics, 2020, Vol 93, pp. 101-112, DOI 10.1016/j.insmatheco.2020.12.001.
  2. J. Liu, H. Zhai, and Z. Wei, "Predicting Automobile Insurance Claims Using Gradient Boosting Machines”, Journal of Data Science, 2017, Vol 15, No 1.
  3. Q. Zhang, Y. Li, and X. Wang, "Hybrid Models for Predicting Auto Insurance Claims Using ML." Expert Systems with Applications, 2022, Vol. 188,115481, DOI: 10.1016/j.eswa .2022.115481.
  4. M. Patel and N. Prajapati,” Predictive Modelling for Auto Insurance Claims Using ML", International Journal of Computer Science and Information Security, 2019, Vol. 17, No 5
  5. L. Chen, Y. Chen, and Z. Huang, “Deep Learning for Predicting Auto Insurance Claims”, Expert Systems with Applications, 2020, Vol. 141.
  6. R. Agarwal, S. Gupta, and P. Verma, "Hybrid ML Models for Auto Insurance Claims Prediction”, Journal of Ambient Intelligence and Humanized Computing, 2021, Vol. 12, No. 6.
  7. A. Malekipirbazari and V. Aksakalli, "Risk Prediction in Auto Insurance: A Bayesian Network Approach”, European Journal of Operational Research, 2015, Vol. 242, No. 2.
  8. Y. Gokgoz and S. Atasoy, "A Comparative Study of Different ML Techniques for Auto Insurance Claim Prediction”, Procedia Computer Science, 2016, Vol 10.
  9. D.Y. Lee, H. Kwon, and S. Y. Choi, "Predicting Auto Insurance Claims Using Deep Learning with Vehicle Telematics Data" IEEE Access, 2017, Vol. 5, DOI: 10.1109/ACCESS. 2017.268 50
  10. E. Albrecher, H. Teugels and J. Beirlan,” Insurance Claim Modelling and Prediction using Extreme Gradient Boosting”, Astin Bulltin, 201 8, Vol. 48, No. 1, DOI: 10. 1017/ asb .2017. 36.
  11. F. Silva, P. Cortez, and M. Santos, "Auto Insurance Fraud Detection with ML: A Case Study", Journal of Risk and Financial Management, 2019, Vol. 12, No. 2, DOI: 10.3390/ jrfm12020075.
  12. G. Zhang, L. Jiang, and Y. Sun, "Utilizing Ensemble Learning Techniques for Auto Insurance Claim Prediction", Computers & Industrial Engineering, 2020, Vol. 14, DOI: 10. 1016/j.cie.2020 .106384
  13. H. N. Nguyen, T. V. Nguyen, and Q. H. Nguyen, "Auto Insurance Claim Prediction Using Hybrid Deep Learning Models", Information Sciences, 2021, Vol. 546, DOI: 10.1016 /j.ins.2 020. 11.042
  14. I. W. Tsai, C. H. Chen, and C. W. Huang, "Predictive Analytics for Auto Insurance Claims Using ML", Expert Systems with Applications, 2022, Vol. 186, DOI: 10.1016/j.eswa. 2021. 11 5946
  15. T. Choudhury, A. Roy, and A. Paul, "Deep Learning for Auto Insurance Claim Prediction: A Case Study", IEEE Transactions on Neural Net- works and Learning Systems, 2020, Vol. 31, No. 9, DOI: 10.1109/ TNNLS. 2020.298057
  16. https://www.kaggle.com/dataset
  17. 8 ML Models Explained in 20 Minutes | Data Camp

Machine Learning business is regular in the insurance market to enhance the efficiency and predictive skills of the insurance industry linear regression as an initial and effective ml method is adopted in this work predicting automobile insurance claim is undertaken using these large datasets which provides the detailed driver characteristics vehicle characteristics and historical claim insights becomes possible to apply linear regression analyses to indicate and predict the likelihood and frequency of upcoming claims to insurers One of the primary motivations for linear regression is a very easy tool has it is pretty simple to use, easy to interpret and at the same time easy to scale it can benefit in managing and resolve the premium pricing and improvement of risk assessment along with the enhancement of the financial stability while applying linear regression the study explains how it can be utilized in auto insurance claims prediction the potential idea of using better ml models for more investigation and its pros and cons this model is mainly assessed in line with its predictive accuracy utilizing metrics reminiscent of mse and r-squared (R2).

Keywords : Machine Learning Techniques; Prediction Model; Auto Insurance Claim.

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe