Optimising Vet Hospital Location Roll-Out
Post-Acquisition / Consumer & Retail / North America / Location Optimisation
$2 BI
Nulla vitae elit libero
$4.3 MI
Fusce dapibus tellus
73%
Ipsum libero
Goal
A leading specialty retailer of premium pet food, supplies, and services, with 1,500+ locations across the US, Canada, and Mexico. Revenues for existing vet hospitals varied significantly, so the ability to correctly identify those more likely to yield higher revenues can deliver significant business value.
Approach
• Developed a segmentation model from customer purchase data, loyalty program, competitor traffic, and market credit card usage, augmented by third-party data to provide additional customer context.
• By studying how customer pet store spend drives purchase behavior in vet stores, the team predicted which pet customers would spend at vet locations for all stores (including pet store locations with no vet).
• Discovered a relationship between the total vet revenue and the number of customers who spend in both pet and vet services, allowing the model to predict total vet revenue.
• Used SHAP techniques to explain each prediction with specific attributes that contributed to the model’s decision-making.
• Ran predictions for all customers across all pet stores, generating a predicted vet revenue for each store. This was used to create an ordered list, coupled with SHAP explanations and additional context.
Interventions
• Delivered a prioritized (and explainable) roll-out action with a production-ready application (and training).
• Enabled the retailer to continue to rerun and revisit the capability as needed.