Optimizing Benefits Selection in View of both Member Population and Organizational Preferences
The present disclosure relates to systems and methods for optimizing benefits plan options offered by an organization through balancing derived population preferences with organizational preferences by analyzing historical selections made by individuals. Census data dividing members of an organization into census divisions may be applied to machine learning algorithm(s) to derive estimated selection preferences of the members. Using selection preferences, costs of various product offering scenarios and overall member satisfaction estimates of the scenarios may be calculated. Product offering scenarios meeting member preference criteria and organizational budget criteria may be presented for review.
1 . A system for optimizing benefits plan options offered by an organization through balancing derived population preferences with organization preferences, the system comprising:
a non-transitory computer readable medium storing population data representing a plurality of individuals, selection data representing one or more respective benefits selections made by each individual of the plurality of individuals, and plan data representing aspects of each benefits selection represented by the selection data; and
processing circuitry configured to perform operations for optimizing benefits plan options, the operations comprising
generating census data for a plurality of members of the organization, wherein the census data divides the plurality of members into at least a set of age brackets and a set of gender brackets,
determining, for each age bracket of the set of age brackets and for each gender bracket of the set of gender brackets of the census data, selection probabilities for a plurality of product offering scenarios, each product offering scenario comprising at least one benefits product, at least one organization cost, and at least one member cost, wherein determining the selection probabilities comprises
applying the census data for the respective age bracket and respective gender bracket to at least one trained machine learning algorithm to obtain a respective selection probability for each product offering scenario of the plurality of product offering scenarios, wherein
the at least one trained machine learning algorithm is trained based upon actual product selections of the plurality of individuals of the population data represented by the selection data, and
for each product offering scenario of the plurality of product offering scenarios, identifying, for the respective age bracket and respective gender bracket, a respective coverage waive probability,
for each product offering scenario of the plurality of product offering scenarios, using the respective selection probability for each age bracket and gender bracket to calculate a) a member perception score for the respective product offering scenario, and b) an estimated organization cost for the respective product offering scenario,
determining, for at least a subset of the plurality of product offering scenarios, a set of the plurality of product offering scenarios meeting criteria including at least one of a maximum organization cost and a minimum member perception score, and
presenting, to a user of a remote computing device, a graphical user interface including information representing the set of the plurality of product offering scenarios.