PetPlate is a premium dog food subscription service where users complete a questionnaire during the subscription flow to receive a personalized meal plan. Based on their answers, users are recommended one of four plans: FreshBaked, FreshCooked, FreshCombo, or Toppers.
Plans to go live 8/15/2025. Feel free to check out the current subscription flow I built that's live.
Client
PetPlate
Role
Product Designer
Year
2025
*For an in-depth case study, please reach out :)
Results
A/B tests resulted in a 5% boost in conversions and a 35% reduction in drop-offs.
The new recommendation algorithm proved effective. About 90% of users recommended FreshCooked completed checkout.
60% reduction in time spent on page.
Problem 1: High Drop off Rates
After thorough data analysis of the subscription flow, steps 10 (plans page) and 11 (entrées page) consistently showed high drop-off rates month over month, averaging 22% and 30%, respectively.
Hypothesis
Users are experiencing decision fatigue, as they’re prompted to choose from up to 4 plans and 8 entrées after already answering 10 questions.
*These two pages have an average time spent on page that exceeds the overall subscription flow average by more than 250%.
Problem 2: Flawed Recommendation Algorithm
During the research and analysis phase of my design process, I identified significant flaws in the recommendation algorithm. For the design changes to be effective, the algorithm must deliver accurate results. If you’re interested in a detailed breakdown of the research and development behind the algorithm improvements, feel free to reach out.
Concerns
FreshBaked, which had the highest checkout rate, was notably absent from the recommendation feature.
The algorithm prioritized recommending the lowest-cost plan, but it was developed without any supporting user research or data-driven insights.
The data made it clear, the current recommendation algorithm wasn’t working.
Recommendation Algorithm update
To support the design changes, we updated the recommendation algorithm to deliver more accurate and personalized meal plans to users. Through a series of UX interviews and the development of a new point-based scoring system, we created a more holistic algorithm (one that goes beyond simply recommending the cheapest plan). We also ensured that FreshBaked, which had previously been excluded despite high performance, was appropriately integrated into the new recommendation logic.
UX interviews -> Themes -> Plan Preferences
We conducted a series of UX interviews to understand why users selected their respective plans.
Using the insights gathered, we identified key themes for each plan and developed a new question featuring these themes as multiple-choice answers.
Prototype & Build
Recommended Plans page: Plans & Entrées in one
With the updated recommendation algorithm, we created a single plans page designed to recommend the best possible plan and reduce decision fatigue.
Results
A/B tests resulted in a 5% boost in conversions and a ~35% reduction in drop-offs.
The new recommendation algorithm proved effective. About 90% of users recommended FreshCooked completed checkout.
60% reduction in time spent on the page.
Continue to monitor A/B test metrics.
Conversion rates
Drop off rates
Checkouts vs. recommended plan
Time spent on page
