Jimmy Jazz’s 8% increase in conversions
Affinity in Recommendations
One of the most common campaigns associated with User Affinity is recommendations. Using recommendations, you can craft tailored experiences based on a user's real-time browsing behavior.
Jimmy Jazz proved that adding these recommendations can play a key role in improving conversion rates. They increased conversions vs. a control group substantially after presenting users with recommended items based on their recent and long-term browsing history.
How does it work
A User Affinity Profile is created. Every time a user interacts with a product, the score of each attribute value is updated by the type of interaction with it (adding the product to cart warrants a higher score than viewing it).
Recency of the interaction also has an impact; the more recent, the higher the impact, for example interactions that occur during the session, will have higher impact than ones that occurred a week ago.
The recommendation strategy uses the User Affinity Profile of each user to retrieve a ranked list of products predicted to be the most relevant to that user. Product Popularity is factored in as well.
Targeting the Correct Audience
Jimmy Jazz knew that returning users convert at a higher rate than new users. As a result, Blue Acorn iCi’s optimization team tested the new User Affinity strategy with 30% of returning users on the homepage. Compared to the control group, they saw:
- 8% increase in conversions
- 4% increase in average order value
- 6.7% increase in click through rate
Setting up your Campaign
- Upload product feed to your Dynamic Yield admin
- This will usually be done during your on-boarding process, however you can always reach out to Support or your CSM if need be
- Define Affinity attributes (columns)
- Discuss this with your CSM or reach out to Support
- Create an Affinity strategy in the Dynamic Yield account
- Set up a Recommendation Campaign in the Dynamic Yield admin
- Lay out an optimization plan
- Map your top items/ categories as well as Audiences to test the Affinity Recommendations
Please sign in to leave a comment.