Advanced Analytics in Actuarial Science: Leveraging Data for Innovative Product Development in Insurance
Keywords:
Advanced Analytics, Actuarial Science, Machine LearningAbstract
Actuaries and statisticalians evaluate insurance risk, pricing, and claims. "Big Data," the development in present data amount, variety, and pace could vary. Research suggests that actuarial science analytics could improve the innovation in insurance products.
The job begins with estimation of actuarial risk and uncertainty. Survival and GLM actuarial approaches work well. Data and theories restrict these methods. Machine learning and artificial intelligence challenge this convention. Big datasets let machine learning approaches find intricate patterns and relationships not possible with conventional approaches. They may combine social networking with wearable sensors. Modern analytics allows actuaries to develop complex risk models from massive data sets: Broad risk categories and historical averages help to increase standard model pricing accuracy. Gradient boosting and random forests might let actuaries modify consumer pricing in response to minor variations in risk profile. Choice of best-risk enhances insurer profit and policyholder fairness.
References
Actuarial Standards Board of the Casualty Actuarial Society and the American Academy of Actuaries. (2014). Casualty reserving standard of practice. https://www.casact.org/
Aggarwal, C. C. (2018). Neural networks and deep learning: A textbook. Springer International Publishing.
Baesens, B., Freitas, A. A., Hair, J. F., & Verbeke, M. (2015). Big data analytics in insurance: Leverage for risk management, fraud detection, and customer insight. John Wiley & Sons.
Berkelaar, A., & Heijnen, A. (2013). A survival analysis approach to model claim durations. ASTIN Bulletin: The Journal of the IAA, 43(2), 321-342.
Brown, I., Zabarah, M., Maniatis, V., & Capra, L. (2016). Explainable artificial intelligence (XAI). arXiv preprint arXiv:1606.05420.
Chen, W., Cheng, H., & Song, Y. (2020). Machine learning for actuarial science. Risks, 8(2), 15.
Chollet, F. (2018). Deep learning with Python. Manning Publications Co.
Cummins, J. D., & Doherty, M. P. (2006). Using survival analysis to model insurance claim durations. The Journal of Risk and Insurance, 73(1), 111-134.
Deming, W. E. (2012). The new economics for industry, engineering, management. Courier Corporation.
Doherty, N. M. (2007). A review of regression methods used for insurance rating. ASTIN Bulletin: The Journal of the IAA, 37(1), 149-167.
Dormann, C. F., McPherson, J. M., Arsenault, L., Gaston, K. J., Roberts, D. R., & Matthews, T. R. (2007). METHODS: Using a suite of statistical models for landscape-scale prediction. Ecology, 88(11), 2862-2879.
Frees, E. W. (2010). Predicting the lengths of future payment streams in insurance: A comprehensive study of survival analysis methods. Casualty Actuarial Society.
Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning. Springer series in statistics New York, NY, USA:. Springer.
Géron, A. (2017). Hands-on machine learning with Scikit-Learn, Keras & TensorFlow: Concepts, tools, and techniques to build intelligent systems. O'Reilly Media, Inc.
Goldstein, M., & Kaplan, E. H. (2014). Users' guide to PROC PHREG. SAS Institute Inc.
Graves, A., Schmidhuber, J., & Hochreiter, S. (2005). Efficient training of recurrent neural networks with long-term dependencies. https://direct.mit.edu/neco/article/9/8/1735/6109/Long-Short-Term-Memory
Harrell, F. E., Jr. (2015). Regression modeling strategies with applications to linear models, logistic regression, and survival analysis. Springer.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112). Springer.
Jordan, M. I. (2007). Machine learning: Probabilistic modeling and algorithmic inference. Springer.
Kleinberg, E. (2014). Society and privacy in the age of networks. Cambridge University Press.
Kuhn, M., & Johnson, K. (2019). Applied predictive modeling. Springer.
Langseth, J., & Nielsen, B. (2003). A survey of statistical methods for modelling insurance claim frequencies. Scandinavian Actuarial Journal, 2003(2), 109-128
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
