- Rialto Administrator
- Super Selector
Creating a Ranking Profile
You can create a new ranking profile, or you can duplicate an existing profile and edit its boosts, and then save it as a new profile.
On the Ranking List page (Market > Manage Profiles and Rankings > Ranking Profiles), select Add Ranking. The Ranking Name Placeholder page appears.
On the right-hand side, enter the name and description for your ranking profile.
Select the ranking boosts. For more information about boosts, see Ranking Boosts.
To adjust the boost weight, select the circle under the weight you want to assign - low, medium, or high. Offers matching boost with the 'High' weight will be shown higher in relation to offers matching boost with the 'Low' weight.
Only the boost that you included in the profile will affect the ranking of offers in the feed. Boosts that you did not include in the profile will not affect the ranking.
To delete a boost, hover your cursor over the line, and select the 'X' to remove the line.
To add additional boost , select Add Criteria.
Click Save to save the ranking profile. You are directed to the Ranking List page, where you will find your new ranking profile. You can now associate this profile with the recommendations feed profile (see Creating a Recommendations Feed Profile).
From the Ranking List (Market > Manage Profiles and Rankings > Ranking Profiles) page, select Duplicate in the row actions list on the profile you wish to duplicate. The profile is duplicated.
The name of your new ranking profile starts with “Copy of ….”. Change that to a meaningful name.
Edit the boost of the profile as necessary.
Click Save to save the profile. You are directed to the Ranking List page, where you will find your new ranking profile. You can now associate this profile with the recommendations feed profile (see Creating a Recommendations Feed Profile).
Editing a Ranking Profile
Any changes you make to the ranking profiles are propagated to the staff. When next opening the feed, your staff will see the resulting changes to their feeds.
From the Ranking List (Market > Manage Profiles and Rankings > Ranking Profiles), select Edit in the row actions list of the profile.
On the page of the selected ranking profile, add, remove, or change the boosts, and modify their weights.
If desired, change the name and the description of the profile.
Click Save to save and return to the Recommendations Profile List page.
Each boost has two characteristics: whether it's scaling or fixed, and whether it's title-level or offer-level.
A scaling boost adds more to an offer based on how closely it aligns with the category, up to the same amount of a fixed boost. A fixed boost adds a flat amount based on whether it matches value configured. For example, "Total sales" will add more boost the more overall sales a title has had, capping out at the same amount as a fixed boost. "Readership level" will add a flat amount if an offer matches the readership level configured.
A title-level boost applies equally to all offers within a group, and is an indication of the content of the resource. Title-level boosts can be used to sort the overall order of titles in a feed. Offer-level boosts apply to specific offers in a work group and can be used to prioritize which offer to recommend. As a rule, use a medium or high weight on title-level boosts, but low weight on offer-level boosts. This will sort feeds first based on best-fit content for your collection, then choose the best offer from within a group based on your policies.
|Ranking Boosts||Description||Recommendations of Use|
|Lowest Price||Select to push offers with the lowest listing price to the top of the feed.||Scaling offer-level. Use a low boost to avoid saturating a feed with inexpensive materials with no regard for quality.|
|Recently Published||Select to push to the top the offers that have been published within the current year.||Scaling title-level. Use high or medium to favor recent materials.|
Select to push to the top the offers that have the highest recent sales within the last ninety days.
|Scaling title-level. Use high or medium to favor trending (rather than overall) sales.|
Select to push to the top the offers that have the highest overall sales (since 2013).
The total sales are calculated based on historical sales trends for works. The information is updated monthly.
|Scaling title-level. Use high or medium to favor overall sales since 2013.|
|Predicted to be of interest to your institution||A predictive signal that boosts offers based on how closely they align to your institution's holdings.||Scaling title-level. Use high or medium to favor titles that might be of interest.|
|Predicted to be Popular (Predicted Sales)||
Select to push to the top the works with the likelihood to have high sales. This signal is predicted based on the similarity of a title to titles that have been popular in the past.
|Scaling title-level. Use high or medium to boost recent titles that are predicted to sell well even if they don't yet have a history of sales.|
|Readership Level||Select specific level(s) that you want to push to the top of the feed. Choose as many or as few levels as you like.||Fixed title-level. Use a medium boost to favor readership levels without overriding other calculated boosts.|
|Platform||Select your preferred electronic platform to push to the top of the feed. Choose as many or as few as you like.||Fixed offer-level. Use a low boost to choose your preferred platform.|
|License||Select your preferred electronic license(s) to push to the top of the feed. Choose as many or as few licenses as you like.||Fixed offer-level. Use a low boost to choose your preferred license.|
Select Yes or No:
|Fixed offer-level. Use a low boost to highlight offers that are DRM-free, downloadable, available for DDA, or available for ATO.|
|ProQuest enhanced records||Records treated by the ProQuest New Titles team for approvals and scheduled purchases.||Fixed offer-level. Use a medium boost to favor ProQuest enhanced records without overriding other calculated boosts.|
Best Practices to Creating Ranking Profiles
Follow the below recommendations to make sure the ranking provides proper visibility to content that is attractive to your institution, and that you do not miss potential offers.
Give high or medium weight to scaling title-level boosts--this will sort feeds first based on content.
Give low weight to offer-level boosts. They will act as tie-breakers among offers with the same content rank. The tie-breaking element acts as the differentiating factor and boosts one offer over another. These boosts can be used to prioritize specific offers based on your institutional policies.
Rialto Default Ranking Profile
The following ranking profile is provided with Rialto out-of-the-box. This profile is general and permissive, and allows the selection staff to do their work in the first weeks after Rialto integration, before the institutional profiles are finalized.
You can modify the profile as you would like or leave it as-is while you are creating the institutional profiles.
|Profile||High Weight||Medium Weight||Low Weight|
|Recent popular||Predicted to be popular||Recently Published|
New for September!
Usage and predicted fit
|Historical usage at your institution||
Predicted to be popular
Predicted to be of interest to your institution
Deleting a Ranking Profile
You can delete a ranking profile, even when it is used in any of your staff’s feeds. If you delete such a profile, the feed results will not immediately change. When next opening the feed, the Ranking drop-down no longer shows the name of the deleted ranking profile, but is replaced by the general word 'Ranking'. However, the boost of the deleted ranking profile still applies. Advise your staff to select an alternative ranking and save their feed.
You can delete a single recommendation feed or several feeds in one action.
On the Ranking List page (Market > Manage Profiles and Rankings > Ranking Profiles), check one or more profiles that you would like to delete.
Select Remove Selected above the list. The profiles are removed.