Recommendations FAQ

What to do if a recommendation has 0% coverage?

Explanation of the issue:

If you have noticed that a recommendation has 0% coverage, it means that the recommendation was not able to find any matching items in the catalog based on selected event attributes in the recommendation metric.

A recommendation can search items only based on the item_id attribute. It means that a data format in events used to generate recommendations must be exactly the same as item_id in the catalog. Additionally, the catalog filter must not be too strict - you must make sure that there are items that match catalog filters.

Example 1: Mismatched event data

Let’s look at this example. Here we have a “Popular Right Now” recommendation template that uses the purchase_example.item_id attribute to check what products customers are buying.

Currently, the coverage is 0% meaning that the recommendation cannot find any item_ids from Purchase_example.item_id attribute values in the catalog test used in the recommendation. The catalog has 2 items, one of them has ID Jeans-001-blue.

There is only one purchase_example event in the database currently and it has the following attributes:

As you can see, the item_id attribute of the Purchase_example event is Jeans-001 which is not in the test catalog item_id column. However, Jeans-001-blue, which is stored in the product_id event attribute matches the item_id of the item in the test catalog. If you change recommendation settings to use the product_id attribute of Purchase_example instead of item_id, the recommendation will be able to find the correct item in the catalog.

In other words, because item_id in the event did not have a "-blue" part, the recommendation could not find the exact match in the catalog data.

Example 2: Too strict or incorrect catalog filters

Let's take a look at another example. We are using the familiar “Popular Right Now” template, but this time we want to show only items with stock levels higher than 10, and the sale attribute equals true.

Here there are no items that match filter conditions. In that catalog, there is only one item, but it has enough stock, but it is not marked as on sale. If you see 0% coverage, try to remove filters one by one to see which filters are causing trouble.

After identifying the filter or combination of filters that are causing the issue, verify if items that match the filters exist in the catalog. If such items exist, check if the filters are set up correctly and if values inserted in the filters can be selected by the filters in the catalog data.