The Precision setting lets you 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. A broader precision allows recommendations to “fall back” in situations where data is insufficient so that some alternative form of recommendations can be presented to the shopper. A narrower precision restricts 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.
Profiles default to the broadest precision, but they can be changed and made more restrictive when needed.
This feature is exclusive to Similar, Cross-sell, Cart-Cross-sell, and Bundle 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 Cross-Sell Rules or Similar Rules, depending on the type of recommendation requested. 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, or the products matching a category or brand rule.
- All other precision options will include curated first before returning other results
- Same type as requested (Similar or Cross-Sell)) will only show the crowd and genomic results for the requested type.
- Let's look at an example of "this shirt" as the seed item for cross-sell. Then the crowd results will be the ones other customers have actually bought with “this shirt”, for example, "those pants". If the Data Science Generator can not find enough crowd data regarding what people bought with "this shirt", it will generate genomic recommendations based on the shirt's attributes. So, people who bought "other products similar to this shirt" also bought "that jacket".
- Opposite type as requested (Cross-Sell or Similar) will show crowd and genomic for the selected recommendation and can backfill with the crowd or genomic of the alternative.
- In the example above, if there aren’t enough cross-sell results for “this shirt”, the Data Science will fill in with other items that are similar to “this shirt”.
- Trending will incorporate Crowd and Genomic fallback recommendations, and will also add top-selling products (category and site-wide) if no better recommendations can be found.
- In rare cases where there are still not enough recommendations after all the levels above are satisfied, the Data Science will incorporate trending items.
- If one or more categories were included in the request, those will be used first to fill in trending items from the requested categories. After that, site-wide trending items will be added.
- This is the default configuration, as it ensures that some results are always returned.
The table below lists all the recommendations that are made when you use Trending, Similar, Cross-sell, or Curated precision for Cross-sell Recommendations.
| Precision | Cross-sell Recommendations |
| Trending | Featured Items - products chosen in a Cross-Sell Product Rule or a Category or Brand rule that matches up with the seed item |
| Cross-Sell Crowd - products bought or owned together by a single shopper | |
| Cross-Sell Genomic - products that were bought with other products that are similar to the seed item | |
| Similar Crowd - similar products that have been viewed together with the seed product | |
| Similar Genomic - similar products that have been viewed with products that are similar to the seed item | |
| Trending in a Category (if a category was provided in the request) | |
| Trending Site-wide | |
|
Similar |
Featured Items |
| Cross-sell Crowd | |
| Cross-sell Genomic | |
| Similar Crowd | |
| Similar Genomic | |
| Cross-sell | Featured Items |
| Cross-sell Crowd | |
| Cross-sell Genomic | |
| Curated | Featured Items |
The table below lists all the recommendations that are made when you use Trending, Cross-sell, Similar, or Curated precision for Similar Recommendations:
| Precision | Similar Recommendations |
| Trending | Featured Items - products chosen in a Similar Product Rule for the seed item |
| Similar Crowd - similar products that have been viewed together with the seed product | |
| Similar Genomic - similar products that have been viewed with products that are similar to the seed item | |
| Cross-sell Crowd - products bought or owned together by a single shopper | |
| Cross-sell Genomic - products that were bought with other products that are similar to the seed item | |
| Trending in a Category (if a category was provided in the request) | |
| Trending Site-wide | |
| Cross-Sell | Featured Items |
| Similar Crowd | |
| Similar Genomic | |
| Cross-sell Crowd | |
| Cross-sell Genomic | |
| Similar | Featured Items |
| Similar Crowd | |
| Similar Genomic | |
| Curated | Featured Items |
Comments
0 comments
Article is closed for comments.