Abstract
We define the nagging predictor, which, instead of using bootstrapping to produce a series of i.i.d. predictors, exploits the randomness of neural network calibrations to provide a more stable and accurate predictor than is available from a single neural network run. Convergence results for the family of Tweedie’s compound Poisson models, which are usually used for general insurance pricing, are provided. In the context of a French motor third-party liability insurance example, the nagging predictor achieves stability at portfolio level after about 20 runs. At an insurance policy level, we show that for some policies up to 400 neural network runs are required to achieve stability. Since working with 400 neural networks is impractical, we calibrate two meta models to the nagging predictor, one unweighted, and one using the coefficient of variation of the nagging predictor as a weight, finding that these latter meta networks can approximate the nagging predictor well, only with a small loss of accuracy.
Subject
Strategy and Management,Economics, Econometrics and Finance (miscellaneous),Accounting
Reference30 articles.
1. Bagging predictors
2. Analyzing bagging
3. Approximation by superpositions of a sigmoidal function
4. Making Tweedie's Compound Poisson Model More Accessible
5. Artificial neural networks architectures for stock price prediction: Comparisons and applications;Di Persio;International Journal of Circuits, Systems and Signal Processing,2016
Cited by
40 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献