Web layer with personalized recommendations
Personalized offers are must in the world of ecommerce. Customizing content is a key part of the customer experience and the proper use of data allows marketers to create relevant experiences that hold attention and generate loyalty.
If you want to use personalization in a more effective way, remember to make use of the many different places on your website where it is possible to use it. One of them is web layer, which can be a good place where you can show personalized products that can encourage customers to make a purchase.
Example of use - Retail industry
Challenge
A client from the retail industry decided to present an additional section of products on the home page, with personalized products, filtered according to gender based on the last viewed product.
A web layer was added to the bottom of the screen on the home page, which contained products from selected brands - women’s, if the last product seen by the user was for women, men’s if for men.
Requirements
Basic elements of AI integration:
-
Tracker
-
Product feed, filled with appropriate custom attributes
-
Transactional events
-
OG tags
How to do it
-
Prepare 2 AI campaigns and remember to take care of proper filtering.
To prepare personalized products narrowed to selected brands and gender:
- Choose the “personalized” campaign type
- Specify the brand filter: include custom brand - and enter the brands you are interested in
- Specify the category filter: include custom - here you can specify whether you are interested in women’s or men’s products
-
Prepare 2 dynamic content campaigns - one for the customer segment whose last-viewed product was female, the other for those whose last-viewed product was male.
In such information is included in the product url, prepare the aggregate (type: Last) for the url parameter in event page visit.
-
Create segments where this aggregate contains the value “female” or “male”.
Read more
- Read more about aggregates
- Read more about creating an AI campaign with the appropriate filters
- Read more about segmentation
- Read more about types of recommendations
