How to use recommendations in emails campaign
Embed personalized recommendation banners into email campaigns.
AB Tasty collects user events associated with USER_ID for data collection. Algorithms are trained for various scenarios such as discovering similar items, finding complementary products, and identifying bestsellers. The Algorithm Builder is used to build recommendations, which can be input-based (like those similar to the last viewed items) or non-input (such as bestsellers and new releases). There's also a data enrichment protocol that includes the exchange of a flat file mapping USER_ID to recommended products. In the near future, an API token will allow direct synchronization with Adobe Campaign.
How It Works
Data Collection
AB Tasty retrieves user events tied to
USER_ID.Algorithms trained (similar, complementary, bestsellers, etc.).
Build Recommendation
Use Ranking Blocks in Strategy Builder.
Input-based (similar to last viewed).
Non-input (bestsellers, new releases).
Data Enrichment Protocol
Exchange flat file (USER_ID → RECO products).
Prerequisites
Ensure navigation events contain
USER_ID.Configure file exchange protocol or direct API access.
Deploying a new email recommendation
Create a recommendation strategy in AB Tasty.
Deploy the recommendation on Email campaign
After save your recommendation strategy, click on "deployment settings" on the bottom of the strategy builder.
If in your Email tool support API request in JSON format you can use the Recommendation API request. Use the first part of the deployment page :
Click on copy icon to have the ID of the recommendation in order to make the request API.
GET https://uc-info.eu.abtasty.com/v1/reco/[SITE_ID]/recos/[RECO_ID]?variables=[VARIABLES]&fields=[FIELDS]RECO_ID
The unique identifier of your recommendation (copied from the platform).
5a936bc0-fbd1-4048-81a8-b94da73178e2
SITE_ID
Your AB Tasty site identifier.
952
VARIABLES
JSON-encoded dynamic variables used by the recommendation
JSON.stringify({
"viewing_item": "46857036202293",
"viewed_items": [
"46855642644789"
]
})
FIELDS
Optional JSON-encoded fields to retrieve from the query. By default, only id.
JSON.stringify([ "img_link", "id", "price", "catalog_page_path", "name", "revenues_last_30_days" ])
If you have an email tool that is compatible with feeds, use the second part of the deployment recommendation page.
Today, we have implemented the following email tools:
If in your Email tool support API request in HTML format you can use the Template feature to have the result of recommendation in HTML.
Then, you can use the second part of the deployment recommendation page to have the code to implemented in your tool.
Today, we have implemented the following email tools:
Last updated
Was this helpful?