Print Email Facebook Twitter Insurance – A Machine Learning Perspective Title Insurance – A Machine Learning Perspective: Predicting Automobile Liability Insurance Pure Premiums Using Machine Learning Methods Author Hes, Robin (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Microelectronics) Contributor Al-Ars, Z. (mentor) Tax, D.M.J. (graduation committee) de Voogd, G.W.H. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Engineering Date 2018-08-17 Abstract This thesis explores the use of machine learning techniques in an effort to increase insurer competitiveness. It asks whether it is possible to accurately estimate the expected financial loss of a given insurance contract and how this information can be used to gain a competitive edge in the business. To answer these questions, some basic principles of insurance are introduced, with a focus on statistical modeling. Furthermore, potentially successful algorithms and techniques are described, like ordinary least squares, generalized linear models (GLMs), generalized additive models, clustering, random forests and gradient boosting trees. It is shown that theory that was originally developed for GLMs, can easily be generalized to other methods, chiefly gradient boosting, with often better results. A new form of evaluation is introduced that helps to rate the efficiency of an insurance portfolio. This, and other metrics are finally applied to several designed models to demonstrate their effectiveness. Subject insuranceMachine Learningpure premium To reference this document use: http://resolver.tudelft.nl/uuid:643ed1a3-5eeb-4fc1-8a92-73a0b72f50cf Embargo date 2019-08-10 Part of collection Student theses Document type master thesis Rights © 2018 Robin Hes Files PDF thesis.pdf 738.25 KB Close viewer /islandora/object/uuid:643ed1a3-5eeb-4fc1-8a92-73a0b72f50cf/datastream/OBJ/view