"The aim of my proposal is to develop a coherent methodology based on classical mathematical statistics for the important area of reserving, transforming it into state-of-the-art mathematical statistics. In doing this, I will use my academic knowledge of modern mathematical statistics, in particular my extended experience in modern smoothing theory.The objectives are:- To develop models based on reported numbers of claims and aggregated claim payments, which provide better insights into the underlying drivers of the claims data- To investigate the use of external data to stabilise the predictions of claims liabilities- To incorporate models which allow for claims inflation in calendar, development year and underwriting year direction- To develop new bootstrap methodologies in order to obtain predictive distributions- Finally to transfer all the above results into a continuous data setting based on structured smoothing.Everything I proposed in this Fellowship is directly linked to what practical actuaries are doing today. They can follow step by step how their current reserves are being changed when adding more and more features of our new methodologies. One can therefore understand the difference between the innovative reserving methods of this project and current methods. It is expected that the suggested working stream will lead to popular methods with a good chance of quickly catching on in the industry. One major global insurer is already advocating such work in light of the increasing regulatory pressure on improved reserving methodologies formulated via Solvency II and it is hoped more will follow when the work develops and gets more widely accessible to practitioners."