Comparative Study of Regression Models and Deep Learning Models for Insurance Cost Prediction

  • Aditya ShindeEmail author
  • Purva Raut
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 940)


In the finance world, Insurance is a product that reduces or eliminate the cost of loss caused due to different risks. There are various factors associated that affect the insurance charges. These factors contribute in formulating the insurance policies. Using machine learning, we can predict insurance charges by developing a model that generalize the entire process. Machine Learning in the Insurance industry would enable seamless formulation of insurance policies with better performance and will time. This study presents how insurance charges can be predicted using various regression models. Also, comparison between the performances of models like Multiple Linear Regression, Support Vector Machine, Random Forest Regressor, XGBoost and Deep Neural Networks is done. This paper provides the most optimal solution using Deep Neural Networks with a root mean square error RMSE value of 0.0695 and model accuracy of 87.95.


Regression Insurance Random Forest Regressor XGBoost Deep Neural Networks 


  1. 1.
  2. 2.
    Gupta, S., Tripathi, P.: An emerging trend of big data analytics with health insurance in India. In: 2016 International Conference on Innovation and Challenges in Cyber Security (ICICCS-INBUSH), Noida, pp. 64–69 (2016)Google Scholar
  3. 3.
    Kaggle Medical Cost Personal Datasets. Kaggle Inc.
  4. 4.
  5. 5.
  6. 6.
    Kayri, M., Kayri, I., Gencoglu, M.T.: The performance comparison of multiple linear regression, random forest and artificial neural network by using photovoltaic and atmospheric data. In: 2017 14th International Conference on Engineering of Modern Electric Systems (EMES), Oradea, pp. 1–4 (2017)Google Scholar
  7. 7.
    Gumus, M., Kiran, M.S.: Crude oil price forecasting using XGBoost. In: 2017 International Conference on Computer Science and Engineering (UBMK), Antalya (2017)Google Scholar
  8. 8.
    Ian, G., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)zbMATHGoogle Scholar
  9. 9.
  10. 10.
    Kansara, D., Singh, R., Sanghvi, D., Kanani, P.: Improving accuracy of real estate valuation using stacked regression. Int. J. Eng. Dev. Res. (IJEDR) 6(3), 571–577 (2018)Google Scholar
  11. 11.
    Yerpude, P., Gudur, V.: Predictive modelling of crime dataset using data mining. Int. J. Data Min. Knowl. Manag. Process (IJDKP) 7(4) (2017)CrossRefGoogle Scholar
  12. 12.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, É.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12(Oct), 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Grosan, C., Abraham, A.: Intelligent Systems: A Modern Approach, Intelligent Systems Reference Library Series. Springer, Cham (2011)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Dwarkadas J. Sanghvi College of EngineeringMumbaiIndia

Personalised recommendations