Abstract: Aspects of the technology described herein can improve the efficiency of a multi-result set ranking model by selecting a better exploration strategy. The technology described herein can improve the use of the result set opportunities by running offline simulations of different exploration policies to compare the different exploration policies. A better exploration policy for a given ranking model can then be implemented. In addition to allocating an efficient amount of result set opportunities to exploration, the selection of exploration results can help reduce performance drop during exploration. Thus, the technology described herein can provide valuable exploration data to improve ranking performance in the long run, and at the same time increase performance while exploration lasts.

Abstract: Methods, computer systems, and computer-readable storage media for modifying an advertising bid for delivering behaviorally-targeted advertising based on affinity scores are provided. A set of affinity scores associated with users belonging to a behavioral targeting segment is received. A bid adjustment factor is dynamically calculated based on a first affinity score of the set of affinity scores; the first affinity score is associated with a first user of the set of users. The bid adjustment factor is used to modify the advertising bid such that the bid reflects an affinity of the first user for the topic associated with the behavioral targeting segment.