Description: Explore a general introduction to uplift modeling, a relatively newer area in machine learning which has been successfully used in retail (Wayfair etc.). The concepts are parallel to the intervention programs in health care, where we are interested in measuring the treatment effects and ultimately directing the right members to the most effective programs, driving the highest value for the programs both from a financial and health outcomes perspective.

Description: The note begins with a short overview of key characteristics of a modern tontine. This is followed by a representation of a tontine flowchart that explicitly displays the components of a tontine and their relationships. The remainder of the note discusses the specifics of those components, including: the valuation and buy-in module, the active life test, settlement options, and periodic payments.