parallax background

Insurance Pricing

Request a demo


steps to create your models


options of cloud deployment


plots and tables to analyse results


increased predictive force on case study

Insurance Pricing

Our product is dedicated to both a pricing manager and a pricing actuary in non-life insurance pricing departments. It automates and enhances all insurance pricing process phases:

  • Data Preprocessing – collects claim data, quotas and external data and performs any data transformations required such as removal of missing values, encoding categorical data or scaling in an optimal way.
  • Risk Modelling – automatically discovers important interactions and selects fair pricing models with traditional actuarial techniques such as standard GLM’s, AI-boosted GLM’s or interpretable actuarial machine learning models.
  • Pricing Optimization – selects an optimal pricing strategy by combining results of risk and conversion modelling to improve technical result and minimize negative selection.
  • Model Deployment & Monitoring – save your project or deploy the best models for production purposes.

Want to see it in action? Request a demo

Pricing Actuary boosted with AI

Standard pricing modelling involves manual fitting of GLM models to catch non-linearities and capture all trends in the policy data. This tedious, resource consuming and error-prone process can be automated by two novel methods offered by insurance pricing module of ActuAI platform:

  • AI-boosted GLMs
  • Interpretable actuarial machine learning models

AI-boosted GLMs allows your actuaries to spend less time on feature interaction analysis as well as coefficient smoothing procedures. Sophisticated machine learning models are black-box – to address this issue we offer interpretable GBMs & neural networks understandable thanks to Explainable AI algorithms dedicated to actuarial processes.

(a) GLM beta coefficient for Driver Age

(b) GLM smoothed beta coefficients for Driver Age

(c) Frequency predictions of Neural Network explained with Ceteris Paribus plot for Driver Age

Figures (a) and (b) shows the standard analysis of frequency modelling done by a pricing actuary. Figure (a) shows the beta coefficient value for the fitted GLM model. To include non-linear effects in GLM, actuaries smooth the beta coefficients for different ranges of selected explanatory variable. In figure (b) thanks to the smoothing procedure younger policyholders have higher betas which will result in higher predicted claim frequencies and thus prices, whereas for policyholders with lower claim frequencies an actuary will set lower GLM betas. Since smoothing procedure and selection of ranges is error-prone and manual + still locally linear, we can use more sophisticated algorithms such as Neural Networks with Poisson Loss to model frequencies, however we would not be able to analyse and interpret betas like in GLM. Thus, ActuAI comes with Explainable AI ceteris paribus algorithm to analyse the effects of varying driver age on predicted frequencies (c).

Automation for managers + Flexibility for actuaries

Our automated machine learning algorithm and comprehensible UI allow building, deploying and analysing results of a pricing model without any programming knowledge in a few minutes.

On the other hand, for most advanced users we offer a possibility to load their own models or data transformations and still benefit from model serving infrastructure as well as other parts of the platform such as XAI. Moreover, your IT department can use our API to plug selected parts of our technology into existing solutions & products.

More details?Download Booklet

Simplified Pricing Process with
ActuAI Platfrom

Use ActuAI cloud-based platform to automate building fair pricing models from weeks to hours thanks to simplified workflow, direct deployment and intuitive reports.