Precision

The Precision setting allows you to choose the types of recommendations that are allowed to be shown in a given profile. In some cases, you may want strict control over which recommendation types are shown, opting to show fewer results or even hide the profile if your preferred results are not available. In other cases you may want to fall back on some broad, generic result types to make sure something is shown in that location, even if the preferred type is not available.

The options for this setting range from Narrow to Broad (left to right).

• A narrower precision will restrict the profile so that recommendations only show if they meet the criteria for the selected type. The narrower setting may result in the profile not showing on certain pages when the minimum threshold of products has not been met.
• A broader precision will allow recommendations to “fall back” in situations where data is insufficient, so that some alternative form of recommendations can be presented to the shopper.

Profiles default to the broadest precision when they are first created, but this setting can be changed and made more restrictive as needed.

Note: The Precision feature is exclusive to Similar, Cross-sell, Cart Cross-sell, and Search Cross-sell recommendations.

Our data science generator analyzes user behavior for each item in the catalog. It also analyzes how those items are related by catalog attributes such as categories, collections, and brands, and how shoppers interact with products owning those attributes.

From this analysis, we are able to generate crowd data for each item (bought together or viewed together), and also genomic data (bought with items like this or viewed with items like this). 

Supported Precisions

• Curated will limit recommendations to the products set in your Similar or Cross-sell Rules. If the seed product does not have one or more products associated with it in a rule, no recommendations will be returned.
  • If merchandisers want to create a "Complete the Look" experience, they would set the Precision Filter to Curated. As a result, the recommendations carousel would only show the pinned products.

The next two precision types will play off each other. If the profile type is set to "Similar", then the next level of precision will be "Cross-sell". If the profile type is set to "Cross-sell", "Cart cross-sell", or "Search cross-sell", then the next level of precision will be "Similar". This will be reflected in the sliding scale of precision. (See the image comparison below these next two definitions.)

• Similar or Cross-sell / Cart cross-sell / Search cross-sell will only apply the crowd and genomic results for the requested type.
• Cross-sell / Cart cross-sell / Search cross-sell or Similar backfills by incorporating recommendations for other products that share product attributes with the one being viewed (helpful when a product is new). 
  • We will show crowd and genomic for the selected recommendation and can backfill with the crowd or genomic of the alternative.
  • For example, a flannel shirt is being used as the seed item for cross-sell. The crowd results would include items other shoppers have bought with that flannel shirt, such as khaki pants. If the Data Science Generator cannot find enough data regarding what people bought with the flannel shirt, it will generate recommendations based on the shirt's attributes. If people who bought other products similar to this shirt also bought a jacket, the jacket will be recommended.

Similar recommendation type	Cross-sell recommendation type

• All will incorporate Crowd and Genomic fallback recommendations, and it will also add top-selling products (category and site-wide) if no better recommendations can be found.
  • This is the default configuration, and it includes the entire hierarchy mentioned above. 
  • Merchandisers can still curate recommendations, and these will show up first. However, with "All" Precision, the system will fill in the rest at all the different precision levels. 

The tables below list all the recommendations that are made when you use Curated, Similar, Cross-sell, or All precision.

"Cross-sell" recommendation type

Featured Items = Products chosen in a Cross-Sell Product Rule or Category/Brand Rules are set up for the seed item

Cross-Sell Crowd = Products bought or owned together by multiple shoppers

Cross-Sell Genomic = Products that were bought with other products that are similar to the seed item

Similar Crowd = Products that have been viewed together with the seed product

Similar Genomic = Products that have been viewed with products that are similar to the seed item

Trending in a Category = Products that are trending (if a category was provided in the request)

Trending Site-Wide = Products that are trending overall in the store

"Similar" recommendation type

Featured Items = Products chosen in a Similar Product Rule for the seed item

Similar Crowd = Products that have been viewed together with the seed product

Similar Genomic = Products that have been viewed with products that are similar to the seed item

Cross-sell Crowd = Products bought or owned together by multiple shoppers

Cross-sell Genomic = Products that were bought with other products that are similar to the seed item

Trending in a Category = Products that are trending (if a category was provided in the request)

Trending Site-Wide = Products that are trending overall in the store