Predictive analytics identified $45M in revenue opportunity to retain profitable facilities
To understand attrition, over 40 hypotheses were developed to identify likely churners, including facility and pharmacy characteristics, customer service, account management details, and billing and contract data to predict the observed attrition behaviour.
The definition of attrition was defined separately for each segment. For Skilled Nursing Facilities (SNF) attrition was defined as cancellation of contract, whereas for Assisted Living Facilities (ALF) attrition was defined as a significant drop in prescription volume
Predict the probability that a facility will attrite in the 4th month from the scoring month (a 3 month lead time) for controllable reasons
Predict probability that the operational scripts will drop more than 80% in future 3m compared to past 12m after the 3m lead time [average scripts in (n+4, n+5 and n+6)/ average scripts in (n, n-1, n-2, …, n-11) < 0.2 A variety of machine learning techniques including Gradient Boosting Machine and Random Forest were used to build advanced predictive models.
The current profitability was considered in prioritizing facilities for retention with a segment-specific intervention strategy based on the drivers of attrition, which varied significantly across high risk segments.
Estimated $40M potential of revenue can be saved through retention targeting of 40% of skilled nursing homes
$5M in revenues could be saved by targeting assisted living facilities
Artificial intelligence through machine learning predictive models
$Framework to programmatically identify facility-level attrition drivers to drive custom interventions at scale