A framework for spatial feature selection and scoping and its application to geo-targeting

Predicting if a particular user clicks on a particular ad is of critical importance for internet advertising. Associations between Internet ad performance data, such as number of clicks or Click Through Rate, CTR, and demographic data may be very weak on the global level, but strong at the regional level. Identifying regions with strong associations of a continuous performance attribute with geo-features can create valuable knowledge for geo-targeted advertising. In this paper, we present a novel framework for interestingness scoping to identify such regions and discuss how such interestingness hotspots can be used for geo-feature evaluation with the goal to develop more accurate prediction models for advertisers. We also present the ZIPS algorithm that takes initial seed zip codes and discovers interestingness hotspots/coldspots, and a geo-feature preselection algorithm which automatically finds promising geo-features and identifies initial seed zipcodes for the ZIPS algorithm. We applied our framework to a large number of geo-spatial data sets, combining data from a major ad network, demographic data from the 2000 Census, and binary feature data from other sources. Our experimental results demonstrate that creating geo-features can double CTR performance for an Ad.