Machine Learning Applications in Actuarial Product Development: Enhancing Pricing and Risk Assessment
Keywords:
Machine Learning, Actuarial Science, PricingAbstract
Risk assessment and competitive pricing are essential to insurance. These goals were achieved by actuaries using statistical models and historical data. The digital age's data volume and complexity provide challenges and opportunities for actuarial science. Machine learning (ML) may use this data stream to enhance pricing accuracy and risk assessment in actuarial product creation.
This study explores ML's impact on actuarial pricing and risk assessment. We discuss actuarial pricing and risk assessment and emphasize the limitations of previous methods in a changing risk environment. We then discuss actuarial-relevant machine learning algorithms.
References
Actuarial Standards Board (ASB). (2014). Using actuarial modeling techniques in non-life ratemaking. Casualty Actuarial Society.
Baesens, B., Freitas, A. A., Giannotti, F., & Viappiani, M. (2014). Handbook of data mining and knowledge discovery (Vol. 14). Springer.
Bhardwaj, N., Gao, P., & Provost, P. (2018). Explainable AI for risk assessment in insurance. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 2217-2226).
Cherkasky, V., & Smola, A. J. (2004). Machine learning for risk assessment. In Financial engineering (pp. 1123-1136). Springer.
Christopoulos, A., Vrontakis, I., & Politis, G. (2020). Explainable artificial intelligence for actuarial modeling: A review. Risks, 8(2), 13.
Einav, L., & Levin, J. (2014). Economics in the age of big data. Science, 346(6210), 1243089.
Feldman, S., & Huttenlocher, A. (2004). Geometric harmonics for shape based object recognition. In International Conference on Computer Vision (ICCV) (Vol. 2, pp. 361-370). IEEE.
Frees, E. W. (2010). Prediction uncertainty for actuarial models. North American Actuarial Journal, 14(1), 1-23.
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of statistics, 29(1), 1189-1232.
Goldstein, M., & Kaplan, W. (2014). Users' guide to statistical reasoning (Vol. 9). Cengage Learning.
Gorunescu, F. (2016). Data mining and machine learning in cybersecurity. John Wiley & Sons.
Green, T., & James, G. (2018. Xgboost: extreme gradient boosting. R package version 0.6-0.
Guo, X., Zhang, L., You, Y., & Luo, Y. (2019). On explainable artificial intelligence for decision support systems. Decision Support Systems, 118, 35-41.
Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural computation, 18(7), 1527-1554.
Hooker, G., & McClure, D. (2014). How big data is different. Peeling Back the Layers of Big Data (pp. 17-28).
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning with applications in R (Vol. 112). Springer.
Jiao, P., Lv, Y., & Liu, Z. (2020). A survey on explainable artificial intelligence for insurance risk assessment. Artificial Intelligence Review, 53(1), 303-331.
Johnson, F. C., & Gupta, M. R. (2018). Fair machine learning for actuarial modeling. Risks, 6(2), 24.
Jordan, M. I. (2011). Derivative check computation of hessian. arXiv preprint arXiv:1106.4815.
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Li, L. (2014). Large-scale video classification with convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1771-1778).
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
