Valuation and Advanced Learning methods for Emerging, global Risks In Actuarial science

The insurance industry faces fundamental changes that will not be tackled by incremental improvements of existing techniques, but call for entirely new insurance pricing paradigms. The dynamics of emerging risks such as cyber and weather related risks need to be handled with little or no past data. At the same time, for more traditional covers the wealth of data that is collected now presents new challenges (e.g., computational or ethical) and opportunities (e.g., statistical power). Bringing together the Leuven-based expertise on machine learning practice for insurance data with the knowledge on stochastic processes, behavioral data and dependencies from the Melbourne team, this PhD project will focus on formulas for discrimination-free insurance pricing, predictive modeling tools for the actuarial valuation of emerging risks and the creation of data analytic tools for a customer-centric, usage based insurance paradigm that bundles selected products and even services. As such, we will design dynamic, responsive and resilient pricing and reserving techniques for traditional but also emerging risk types, including machine learning methods that balance predictive value and acceptability by major stakeholders (e.g., explainable to management, discrimination-free pricing). Access to real data and strong links with practice will ensure applicability and relevance of our developments.