A Search Engine That Learns.
Jeffrey K. Elser, John Paxton · Computational intelligence · 2005
Tuning a local Web site to generate better local search results is a time consuming and tedious process. In this paper, we describe a technique that can help to automate this process. Specifically, when a genetic algorithm is applied to a local search engine’s parameters, the performance of the local search engine can be improved. Once good values for the search engine have been learned, it is easy to identify local Web pages that are candidates for further improvement.