Actuarial reserving techniques have evolved from the application of algorithms, like the chain-ladder method, to stochastic models of claims development, and, more recently, have been enhanced by the application of machine learning techniques. Despite this proliferation of theory and techniques, there is little guidance beyond heuristics on which reserving techniques should be applied and when. In this paper, we revisit traditional reserving techniques within the framework of supervised learning to define optimal techniques and hyper-parameter choices. We show that the use of optimal techniques can lead to more accurate reserves and investigate the impact on capital requirements.

Outcomes:
* Attendees will be introduced to the main ideas of machine learning, such as predictive accuracy and loss functions.
* We will also cover several different IBNr reserving techniques
* By understanding and using the framework we present, attendees will be potentially able to increase the predictive accuracy of their reserving work.