Einstein Recommendations Showing Purchased Items: How to Fix
A marketing manager uses Einstein recommendations on their website, but customers are receiving suggestions for products they already purchased. What is the most likely cause?
Quick Answer
The answer is that the recommendation model is not filtering out previously purchased items. This is the most likely cause because Einstein Recommendations relies on customer purchase history to generate personalized suggestions, but unless the model’s filtering logic is explicitly configured to exclude items a customer has already bought, those same products will continue to appear in the recommendations. On the Salesforce AI Associate exam, this scenario tests your understanding of recommendation model configuration versus data sync or algorithm type issues—a common trap is assuming the problem is a data lag when it is actually a missing exclusion rule. To remember this, think of it as a “purchase blind spot”: the model sees what was bought but doesn’t know to hide it unless told. A quick memory tip: “If it’s already in the cart, keep it out of the heart.”
⚠ Common exam trap
Salesforce often tests the distinction between data source issues (e.g., catalog not updated) versus model configuration issues (e.g., missing filters), and the trap here is assuming the problem is a data sync failure when it is actually a missing business rule in the recommendation logic.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
The recommendation model is not filtering out previously purchased items.
C is correct because the most likely cause is that the recommendation model is not configured to exclude previously purchased items. Einstein Recommendations uses customer purchase history to personalize suggestions, but if the model's filtering logic does not explicitly remove items the customer has already bought, those items will continue to appear in the recommendations. This is a common oversight in model configuration rather than a data sync or algorithm type issue.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The product catalog is not updated with purchase history.
Why it's wrong here
Purchase history is separate from catalog.
- ✗
The model is using real-time browsing data that includes past purchases.
Why it's wrong here
Real-time data does not include past purchases.
- ✓
The recommendation model is not filtering out previously purchased items.
Why this is correct
Einstein recommendations can exclude purchased items.
- ✗
The recommendations are based on collaborative filtering without personalization.
Why it's wrong here
Personalization considers purchase history.
Go deeper
Related to this question
About these practice questions
One of 753 original AI Associate practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on AI Associate
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A nonprofit uses Einstein Recommendations to suggest donations. They notice that the recommendations are not relevant. Which best practice should they follow to improve relevance?
medium- ✓ A.Verify that the Recommendation object has enough historical interaction data and that events are correctly tracked.
- B.Set a data retention policy to delete records older than 30 days to keep data fresh.
- C.Increase the number of recommended items to 10 to give more choices.
- D.Display recommendations on every page, including the donation receipt page.
Why A: Einstein Recommendations rely on historical interaction data to learn user preferences and make personalized suggestions. Ensuring that the Recommendation object has enough interaction data and that events are correctly tracked is essential for accurate predictions. Option B is incorrect because deleting records older than 30 days removes valuable historical data, which reduces the model's ability to detect patterns and improve relevance. Option C is incorrect because increasing the number of recommended items does not inherently improve relevance; it can lead to decision fatigue and may serve less relevant suggestions. Option D is incorrect because displaying recommendations on every page, especially on a donation receipt page where users are not actively exploring, is unlikely to generate meaningful interactions and can degrade relevance.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI Associate practice question is part of Courseiva's free Salesforce certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI Associate exam.