Customer Relation


Case I:

Predicting attrition helps pharmacy distributor identify $45M opportunity to boost customer retention

Wholesale drug distributors have experienced strong competition and consolidation leaving only a few surviving distributors to service most of the US market. Our client, a leading distributor of drugs to long-term care facilities was losing business to competitors over the last several quarters. The hypothesis was that facilities were leaving for addressable reasons such as poor response times, inaccuracies in executing orders, or delays in addressing customer complaints. This client wanted to understand the drivers of attrition and proactively identify at-risk accounts to develop effective retention strategies.
The solution proposed maximizing the total customer lifetime relationship value, with the first phase focused on determining the drivers of attrition. Involuntary attrition from the client terminating the relationship or closing a facility was not included in the initial scope.
A leading provider of pharmacy services
Client was losing business from long term care facilities and wanted to develop strategies to address high attrition

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

Nursing Facilities: Estimate propensity to attrite in the 4th month

Predict the probability that a facility will attrite in the 4th month from the scoring month (a 3 month lead time) for controllable reasons

Assisted living: Estimate propensity for “At-risk” facilities (with a >80% drop in scripts in future 3m

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.

  • Based on our analysis, the following insights were provided to address customer pain points
  • Facilities served by pharmacies with high clear time percentages* & high satisfaction scores attrite less
  • Facilities that experience calls with high average speed of answer (ASA**) and high rate of abandoned calls attrite more
  • Facilities with high number of active months*** in the past 12 months attrite less
  • Clear time percentage refers to the number of prescriptions filled correctly and within time ** ASA is average amount of time it takes for calls to be answered *** Active months are the ones with non-zero script volume
Ensuring high service levels through close monitoring of drug supplies, customized kiosks for easy order placement, and locating pharmacies in close proximity to facilities can significantly improve retention

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