Ecommerce ops · Production
Dynamic Yield Predictive Targeting increases Revenue per User by 54.1% for an English sports team
The problem
An English sports team needed to identify the optimal product recommendation strategy for each of its audience segments and lacked an automated way to determine which test variation to serve to which traffic segment.
Workflow diagram · grounded in source
1
A/B test launch
trigger
“Convert an ordinary A/B test into an incredible personalization opportunity”
2
Segment-level winner identification
ai_action
“Automatically identify the winning test variation for each of its traffic segments”
3
Personalized recommendation delivery
output
“Increase Revenue per User by a whopping 54.1% within a couple of weeks”
Reported outcome
Predictive Targeting automatically identified the winning test variation per segment, converting an ordinary A/B test into a personalization opportunity and increasing Revenue per User by 54.1% within a couple of weeks.
Reported metrics
Revenue per User54.1%
Time to resulta couple of weeks
Reported stack
Dynamic YieldPredictive Targeting
Frequently asked questions
What did this team achieve with this AI workflow?
Predictive Targeting automatically identified the winning test variation per segment, converting an ordinary A/B test into a personalization opportunity and increasing Revenue per User by 54.1% within a couple of weeks.
What tools did this team use?
Dynamic Yield, Predictive Targeting.
What results were reported?
Revenue per User: 54.1%; Time to result: a couple of weeks (source-reported, not independently verified).
How is this ecommerce ops AI workflow structured?
A/B test launch → Segment-level winner identification → Personalized recommendation delivery.