Description: Machine learning algorithms fit models based on patterns identified in data and can be very complex. In this report, we describe and illustrate a range of methods for interpreting machine learning models from the growing field of Interpretable Machine Learning (IML).

Description: In this Society of Actuaries (SOA) Research Institute report, authored by consultants from Milliman, Inc. (Milliman) we aim to study the effects of hurricanes on human health: whether there is a relationship between hurricanes and the observed prevalence of healthcare utilization or certain health conditions among the affected population, whether this relationship can be observed through a healthcare utilization dataset, and whether there is an interaction between this observation and metrics of socioeconomic vulnerability.

Description: This webcast will detail interpretable machine learning techniques for participants to gain an intuition and understanding about the use of these techniques. We will discuss how to apply them, how to understand them, and how to avoid potential pitfalls.