Evaluate Post-Purchase Recommendation Emails
WayfairApplied Scientist · Onsite
Last updated
Evaluate post-purchase recommendation emails through incremental profit, useful timing, customer eligibility, randomized holdouts, and unsubscribe or complaint guardrails.
A retailer proposes sending recommendation emails after a purchase. Decide whether the feature is worth building and how you would test it. Explain the recommended products, timing, business value, and possible harm before selecting a model.
Constraints & Assumptions
The reported discussion emphasized product and business reasoning. It raised retention versus acquisition cost and negative effects such as unsubscribes and spam complaints. Treat lower retention cost as a hypothesis to validate for this business, not a universal fact.
Clarifying Questions
What outcome would justify the email? Which customers are eligible and willing to receive this channel? Are recommendations complementary products, replenishment, or another category? What contact-frequency and timing limits apply?
Follow-up questions
- How would you distinguish an email-caused purchase from one that would occur anyway? What if open rates rise but unsubscribes also rise? How would recent returns or a poor delivery experience change eligibility?
Solution walkthrough is for members
Get the full walkthrough with reference code and complexity analysis, plus Kitty Coach at 300 messages a day. Hints, the code runner and community answers stay free.