Data-driven incentive alignment in capitation schemes

This paper explores whether big data, taking the form of extensive high dimensional records, can reduce cost adverse selection by private insurers in government-run capitation schemes, such as Medicare Advantage. We argue that using data to improve ex ante precision regressions is unlikely be helpful. Even if types become essentially observable, dimensionality covariates makes it infeasible precisely estimate serving a given type: but not necessarily interpretable. gives an informed operator scope select are relatively cheap serve. Instead, we used align incentives forming unbiased and non-manipulable post estimates operator’s gains from selection.