Autocalibration and Tweedie-dominance for insurance pricing with machine learning
From MaRDI portal
Publication:2665871
Abstract: Boosting techniques and neural networks are particularly effective machine learning methods for insurance pricing. Often in practice, there are nevertheless endless debates about the choice of the right loss function to be used to train the machine learning model, as well as about the appropriate metric to assess the performances of competing models. Also, the sum of fitted values can depart from the observed totals to a large extent and this often confuses actuarial analysts. The lack of balance inherent to training models by minimizing deviance outside the familiar GLM with canonical link setting has been empirically documented in W"uthrich (2019, 2020) who attributes it to the early stopping rule in gradient descent methods for model fitting. The present paper aims to further study this phenomenon when learning proceeds by minimizing Tweedie deviance. It is shown that minimizing deviance involves a trade-off between the integral of weighted differences of lower partial moments and the bias measured on a specific scale. Autocalibration is then proposed as a remedy. This new method to correct for bias adds an extra local GLM step to the analysis. Theoretically, it is shown that it implements the autocalibration concept in pure premium calculation and ensures that balance also holds on a local scale, not only at portfolio level as with existing bias-correction techniques. The convex order appears to be the natural tool to compare competing models, putting a new light on the diagnostic graphs and associated metrics proposed by Denuit et al. (2019).
Recommendations
- Boosting insights in insurance tariff plans with tree-based machine learning methods
- Bias regularization in neural network models for general insurance pricing
- Response versus gradient boosting trees, GLMs and neural networks under Tweedie loss and log-link
- A Markov-modulated tree-based gradient boosting model for auto-insurance risk premium pricing
- Actuarial intelligence in auto insurance: claim frequency modeling with driving behavior features and improved boosted trees
Cites work
- Bias regularization in neural network models for general insurance pricing
- Expectation dependence of random variables, with an application in portfolio theory
- Global dependence stochastic orders
- Local Regression and Likelihood
- Making Tweedie's compound Poisson model more accessible
- Model selection based on Lorenz and concentration curves, Gini indices and convex order
- Stochastic orders
Cited in
(21)- Bias regularization in neural network models for general insurance pricing
- Testing for more positive expectation dependence with application to model comparison
- Deep quantile and deep composite triplet regression
- Boosting insights in insurance tariff plans with tree-based machine learning methods
- Local bias adjustment, duration-weighted probabilities, and automatic construction of tariff cells
- Isotonic recalibration under a low signal-to-noise ratio
- Bayesian CART models for insurance claims frequency
- Model selection with Gini indices under auto-calibration
- Telematics combined actuarial neural networks for cross-sectional and longitudinal claim count data
- Testing for auto-calibration with Lorenz and concentration curves
- Convex and Lorenz orders under balance correction in nonlife insurance pricing: review and new developments
- On duration effects in non-life insurance pricing
- Enhancing actuarial non-life pricing models via transformers
- From point to probabilistic gradient boosting for claim frequency and severity prediction
- Transformers-based least square Monte Carlo for solvency calculation in life insurance
- Bayesian cart models for aggregate claim modeling
- A hybrid deep reinforcement learning method for insurance portfolio management
- Isotonic Regression for Variance Estimation and Its Role in Mean Estimation and Model Validation
- Neural Networks for Insurance Pricing with Frequency and Severity Data: A Benchmark Study from Data Preprocessing to Technical Tariff
- Auto-calibration tests for discrete finite regression functions
- Title not available (Why is no real title available?)
This page was built for publication: Autocalibration and Tweedie-dominance for insurance pricing with machine learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2665871)
