I manage a consumer marketplace product and I'm trying to track unique product views. Right now we only fire an event for generic product views and are having a hard time answering questions like: How many unique products does a user view in a day/week? How many unique products does a user view prior to their first purchase? Etc. How do you recommend we implement tracking unique product views in mixpanel?
Hi Daniel C., Please stand by as I search the Mixpanel knowledge base for an AI-powered answer. I normally take about 15 seconds or so. In case AI cannot answer your question, feel free to reach out to Mixpanel support at mixpanel.com/get-support. If you have follow-up questions for this thread, please tag me again with your question: @kapa.ai <follow-up question> 👋
Feel free to ask a follow-up question once I've answered by mentioning me with @kapa.ai
To answer questions about unique products viewed per user, you’ll want to: 1. Model product views as one event with a stable product identifier property
- Use a single event, e.g. Product Viewed / product_viewed.
- Include a product identifier as an event property, e.g. product_id or sku.
- Avoid creating separate events per product; use properties instead. This follows Mixpanel’s guidance to keep events as actions and use properties for context (similar to Page Viewed with Page Name). [Events best practices]2. Be consistent about identity (distinct_id)
- Make sure all view events and purchase events use a consistent distinct_id so per-user calculations and funnels are correct. [Identity overview]3. How to measure “How many unique products does a user view in a day/week?”
In an Insights report:
- Event: Product Viewed
- Measurement:
- Choose Event Property Values Per User → Aggregate Property per User.
- Property: product_id.
- Function: Distinct count (this computes “distinct product_id values per user”). [Aggregate per user]
- Aggregation:
- Then choose how to aggregate across users, e.g. Average or Distribution to see:
- “Average number of unique products viewed per user per day/week”
- Distribution of users by unique products viewed (0–1, 2–3, etc.). [Measurements; Aggregation examples]4. How to measure “How many unique products does a user view prior to their first purchase?”
Use a Funnel with behavioral properties:
- Funnel steps:
1. Step 1: Product Viewed
2. Step 2: Purchase Completed (or your equivalent)
- Add a Behavioral Property between Step 1 and Step 2:
- Type: Aggregate Property per User
- Event: Product Viewed
- Property: product_id
- Function: Distinct count
- This computes, per user, how many distinct products they viewed between first satisfying step 1 and first satisfying step 2. [Behavioral properties]5. If you just need overall “unique products viewed” (not per user)
- In Insights, use an Aggregate Property measurement (not per user) with:
- Event: Product Viewed
- Property: product_id
- Function: Distinct count
- This answers things like “How many unique products were viewed in the last 30 days?” [Aggregation examples]6. Implementation checklist
- Event name: product_viewed
- Required event properties:
- product_id (stable unique identifier)
- Optional: category, price, brand, etc. to enable richer breakdowns later (similar to Cart Analysis patterns). [What to track; Ecommerce analytics]
- Ensure distinct_id strategy is correct so user-level metrics (uniques, per-user aggregates, funnels) are reliable. [Identity overview]If you share your current event name and properties, I can map them directly to the exact Insights and Funnel configurations you’d use.
kapa.ai is still learning and improving, please let me know how I did by reacting below.
ℹ️ Tip: Mention @kapa.ai in the thread for follow-ups or DM the app for 1-to-1 help.
