In this article, you can find a list of the most common use cases connected to the personalization of customer experience. The list below should help you find the one that best suits your needs and a guide on how to set it up.
E-commerce Goal: Activation, Repeated purchases, Cross-sell
Example Usage: Personalised product recommendations show the most relevant products for each customer based on their product views and purchases. This use case increases customer shopping experience by increasing personalization. It could be used to activate a customer and cross-selling additional products to existing customers and increasing their loyalty.
Ideal Placements: Homepage, Campaigns
- Product catalog
- Event tracking for the following events: view product, add to cart, purchase product
This guide will help you to understand how to set up personalized product recommendations to show the most relevant products for each customer.
What are the personalized product recommendations use cases?
There are two options for setting up this use case:
- Show products which customer has recently interacted such as last viewed products. This option should be preferred if recent interactions are more important than longer customer interactions history. For this option, you should use the Customer recent interactions template.
- Show products that are the most relevant for a customer by analyzing customer interactions and finding similar customers that viewed or purchased similar products as a target customer. This option could be set to capture customer preferences on long interaction history and therefore it works well for loyal customers (customers with a lot of interaction history). For this option, we will use Personalised Recommendations for You Template.
In this example, we will work with the events shown in the following picture
E-commerce Goal: Repeated purchases
Example Usage: Reactivate customers with personalized campaigns containing relevant products.
Ideal Placements: Email campaigns
Requirements: Product catalog, Event tracking for the following events: purchase product, view product, add a product to cart, at least several months of these data
Setup: We suggest using the Personalised Recommendations for You Template since it provides the best recommendations based on the preference of other similar customers.
E-commerce Goal: Activation and Repeated Purchases
Example Usage: We would like to show customers the top products from the category that they are currently viewing.
Ideal Placements: Category page
Requirements: Data mapping for events that denote customer interactions with items that represent similarities such as view_item and purchase_item
Setup: In this use-case, we suggest using the Metric based category” template.
E-commerce Goal: Repeated purchases, Cross-sell
Example Usage: Personalised product recommendations show the ranked products from category for each customer based on their product views and purchases. This use case enhances the customer shopping experience while interacting with the category page.
Ideal Placements: Category page, Homepage
Requirements: Event tracking for the following events: purchase product, view product, add product to cart, at least several months of these data.
Product catalog with columns:
- Category column (required): column called e.g. “category_id” that contains string values. It can be single category (e.g. "t-shirt") or list of categories (e.g. "t-shirt;blue"). In the case of category list, individual categories have to be separated by a delimiter (e.g. "t-shirt;blue;man", where "t-shirt", "blue" and "man" are categories and ";" is delimiter).
- Datetime column (optional): column called “date_added” of values like “2019-01-01” indicating when a product was added to the catalog. You have to mark it as
date_added(label in catalog mapping import) when catalog is imported.
Setup: We suggest using the Personalised category page template that is designed for the ranking of items from a specific category.
Category column should be always imported as a string e.g. "t-shirt" or "t-shirt;blue". Please, do NOT use list type for import.
You do NOT need to track categories in the events. On the contrary, it has to be presented in the product catalog.
Updated about a year ago