The arrival of various types of data poses several challenges to actuaries. They can integrate them in their pricing models, or use them to monitor insurance activities.
In this week of lectures, we will introduce state-of-the-art statistical techniques to model telematic data, text data, images, and network information.
How to use data obtained using connected objects, such as GPS boxes in cars? Can we extract interesting information from satellite images? How to use email exchanges with insureds to detect fraud or to predict churn rates? Can we use social networks to offer new insurance products in a (small) community? These are the questions we aim to answer.
Some (hands-on) case studies will be conducted during this week, with R.