Using the automatic self-learning scorer, Using keymatches to guide users to urls – Google Search Appliance Creating the Search Experience User Manual
Page 41
Google Search Appliance: Creating the Search Experience
Best Practices
41
Using the Automatic Self-Learning Scorer
If you enable advanced search reporting, the search appliance uses its automatic-self learning scorer.
This feature automatically analyzes user behavior and the specific links that users click on for specific
queries to fine tune relevance and scoring. The search appliance uses advanced statistical regression to
determine the statistical significance of user behavior, and adjusts for trust bias (that is, users clicking
on the first result solely because it's first). Thus, over time, results become more and more precise
without the need of administrator intervention.
The learning-module runs daily, and learns over a 90 day window. It has the capability to forget old user
behavior, and learn from new ASR data. It is not possible to remove ASR data without waiting for the 90
day window to pass.
You may allow/disallow the scorer to use the information learned by the learning module. However,
even if the scorer is not allowed to use the data gathered by the learning module, no information is lost.
As long as ASR is activated, the learning module continues to learn. If the scorer is allowed to use that
information at a later point, it immediately begins using everything learned over past days.
To deactivate the automatic self-learning scorer, navigate to the following URL: http://
To activate the automatic self- learning scorer, navigate to the following URL: http://
Using KeyMatches to Guide Users to URLs
A document might not be in the search index or might not appear among the highest search
results. However, it might be valuable to users as a search result. You can promote such documents in
the results by using KeyMatches. A KeyMatch guides users to recommended links, and appear when a
user enters a specific search term.
Because a KeyMatch is specific to a front end, you can aim it at specific types of end users, as shown in
the following example. Suppose you administer a search appliance for an e-commerce business,
mediacompany.com. This business sells DVDs online in various countries. The business maintains an e-
commerce website with a home page, www.mediacompany.com, This home page contains links to pages
for end users in different regions, including North America, South America, Europe and the Middle East,
Asia, Australia, and Africa.
You know that when end users search for “new movies,” they are most interested in navigating to http://
mediacompany.com/DVD/recentreleases. You might provide this link on top of the search results as a
KeyMatch, as shown in the following figure.
KeyMatches are not set up by default. You create a KeyMatch for a specific front end by associating a
search term to a specific URL and specifying a title for the match. In the previous example:
•
The search term is “new movies”
•
The URL is http://mediacompany.com/DVD/recentreleases
•
The title is “New DVD releases”