• Corpus ID: 18429744

Neural Networks Ν. Glms in Pricing General Insurance

  title={Neural Networks Ν. Glms in Pricing General Insurance},
  author={Julian Lowe Chairman and Louise Pryor},
1. Executive Summary Neural Networks are often referred to, with awe, as some mysterious representation of the human brain that can "solve" problems. They have also been referred to in previous GISG papers as having potential applications to general insurance pricing or reserving. The purpose of this paper is to remove some of this awe by explaining what Neural Networks are, how they compare with traditional statistical models, and consider what scope there is for their use in general insurance… 
Computational intelligence with applications to general insurance: a review
It is argued that most of the problems that actuaries have to deal with in the context of non-life insurance can be usefully cast in the framework of computational intelligence, and the role of statistical learning in actuarial modelling is explored.
Machine Learning in P&C Insurance: A Review for Pricing and Reserving
The applications of machine learning to the actuarial science field is reviewed and the current state of the art in ratemaking and reserving is presented and the future trends of machineLearning for the insurance industry is summarized.
Machine Learning in Property and Casualty Insurance: A Review for Pricing and Reserving
This work aims to review the applications of machine learning to the actuarial science field and present the current state-of-the-art in ratemaking and reserving, and summarizes the future trends of machineLearning for the insurance industry.
Neural Networks in Insurance
The goal is to predict customer churn in household insurance policies using statistical models and artificial intelligence to identify who and how many customers will cancel their policy.
A practical support vector regression algorithm and kernel function for attritional general insurance loss estimation
A bespoke kernel function that preserves the statistical features of the loss data is derived from first principles and called the exponential dispersion family (EDF) kernel, and the kernel is applied to an insurance loss estimation exercise for homogeneous risk of three different insurers.
Assessing the Performance of Random Forests for Modeling Claim Severity in Collision Car Insurance
This paper builds two reference models, a generalized linear model and a generalized additive model, relying on a log-normal distribution of the severity and including the most significant factors, and compares the prediction performance of the different models using the relative error, the root mean squared error and the goodness-of-lift statistics in combination with goodness- of-fit statistics.
Risk factors selection with data mining methods for insurance premium ratemaking
  • Amela Omerašević, Jasmina Selimović
  • Business, Computer Science
    Zbornik radova Ekonomskog fakulteta u Rijeci: časopis za ekonomsku teoriju i praksu/Proceedings of Rijeka Faculty of Economics: Journal of Economics and Business
  • 2020
The application of the data mining method in this paper aims to improve the results in the process of non-life insurance premium ratemaking, by improving the choice of predictors or risk factors that have an impact on insurance premium rates.


Introduction to the theory of neural computation
This book is a detailed, logically-developed treatment that covers the theory and uses of collective computational networks, including associative memory, feed forward networks, and unsupervised learning.
Generalized Linear Models
This is the Ž rst book on generalized linear models written by authors not mostly associated with the biological sciences, and it is thoroughly enjoyable to read.
Continuous valued neural networks with two layers are sufficient
  • Continuous valued neural networks with two layers are sufficient
  • 1988