Abstract
Machine learning techniques make it feasible to calculate claims reserves on individual claims data. This paper illustrates how these techniques can be used by providing an explicit example in individual claims reserving.
Acknowledgements
I would like to kindly thank Christoph Buser (AXA-Winterthur), Simone Elmer (Helsana), Gareth Peters (University College London), Peter Reinhard (AXA-Winterthur) and Patrick Zöchbauer (ETH Zurich) for sharing their views on data science and claims reserving. These views provided the essential pieces that are combined in this work. Moreover, I would like to thank Dan Murphy (Trinostics), Esbjörn Ohlsson (Länsförsäkringar) and Ulrich Riegel (Munich Re) for providing remarks on an earlier version of this manuscript.
Notes
No potential conflict of interest was reported by the authors.