Feature Pack 3Feature Pack 5Feature Pack 2Feature Pack 4

Example: Fine-tuning search rule boost factors using store preview data

In store preview, you can see the relevancy scores that the search engine assigns to each catalog entry listed in search results. By understanding these relevancy scores, you can assign an appropriate boost factor to ranking criteria when creating a search rule that uses the Change Search Result Order action. You can also use store preview to see the effect of your boost factor on the relevancy scores of catalog entries.

A boost factor is a number that is added to the relevancy score of catalog entries in search results. For example, if you specify a boost factor of 3 for all catalog entries manufactured by IBM, then the search engine increases the relevancy score of these catalog entries by 3.

In this example, you want to create a search rule in the Madisons starter store that boosts coffee makers manufactured by AromaStar in the search results. Without a search rule, the AromaStar coffee makers are listed lower in the search results than you would like. This procedure illustrates how to use store preview to assign an effective boost factor to the AromaStar brand so that AromaStar coffee makers are listed higher than other brands in the search results.

Procedure

  1. Open the Marketing tool.
  2. Use store preview to see the relevancy scores that the search engine assigns to coffee makers when no search rules are applied:
    1. Select File > Store Preview.
    2. Click Launch Store Preview.
    3. In the search keyword box, type coffee maker and click the search icon.
      The search results display.
    4. To display the relevancy scores for each catalog entry in the search results, change the search results to list view, instead of grid view, by clicking the following icon in the top-right corner of the search results:
      List view

      For each coffee maker, the relevancy score is displayed beneath the coffee maker description, as shown in this example:


      Search before after assigning a boost factor
      Note the following details in the previous screen capture:
      • There is one AromaStar coffee maker listed tenth in the first page of search results. The search engine has assigned a relevancy score of 1.5426886 to this coffee maker. All other AromaStar coffee makers are listed on subsequent pages of the search results because their relevancy scores are even lower.
      • The Sharpson coffee maker listed at the top of the search results has a relevancy score of 3.8237567. This is the highest relevancy score for coffee makers.

      To appear higher in the search results than the Sharpson coffee maker, the AromaStar coffee makers must have a relevancy score that is higher than 3.8237567. Based on this store preview data, you can see that by assigning a boost factor of 4 to AromaStar coffee makers in your search rule, these coffee makers will have the highest relevancy scores for coffee makers.

  3. Create and activate a search rule that uses the Change Search Result Order action to boost coffee makers manufactured by AromaStar by a boost factor of 4. The search rule looks like this:

    Search rule to boost AromaStar coffee makers
  4. Use store preview to see how the boost factor in the search rule has elevated AromaStar coffee makers in the search results:
    1. Select File > Store Preview.
    2. Click Launch Store Preview.
    3. In the search keyword box, type coffee maker and click the search icon.
      The search results display.
    4. To display the relevancy scores for each catalog entry in the search results, change the search results to list view, instead of grid view, by clicking the following icon in the top-right corner of the search results:
      List view

      The AromaStar coffee makers are now listed higher in the search results than other coffee makers, and they show a relevancy score that has increased by 4:


      Search results after assigning a boost factor

Results

By analyzing store preview data, you can assign a boost factor in your search rule that produces the results you want on the storefront.