IFoA Asia Conference 2025: call for speakers

An example of a good submission:

Why isn’t machine learning (ML) used routinely in reserving as it is in personal lines pricing?

Although there is widespread interest in ML, we see the same questions come up time and time again on difficulties and obstacles to incorporating ML into reserving. These are topics of substance with no single, easy answer and include questions such as:

• why use ML for reserving in the first place?
• how do you get your stakeholders (including auditors) on board with using ML?
• how can we research and apply ML techniques if we don’t have access to granular transactional data?
• how do you incorporate judgement or external information into an ML-based reserving process
• are actuaries going to be replaced by data scientists?

In this session we will have a panel discussion featuring various members of the Machine Learning in Reserving Working Party (MLRWP) and we will discuss these points and others. The MLRWP has shared many of our findings and material in talks and on our blog.

This will be delivered virtually and will be a high-level session rather than a technical one. It should be of interest to actuaries at all levels with an interest in ML including senior actuaries and team leaders who are interested in using ML in the reserving process and may be asking many of these same questions.