Abstract: An advertising network can provide mechanisms to publishers with which the publishers can influence the relevance of the advertisements provided by the advertising network for display with the publisher's web sites. Such mechanisms include bid boosts, discounts and rank boosts, each of which, either directly or indirectly, can increase or decrease the likelihood that an advertising network will provide a advertisement, targeted by these mechanisms, to the publisher's web pages. Each of these mechanisms also enable the publisher to sacrifice ad-generated revenue for the sake of more relevant advertisements. The advertising network can also provide an interface through which a publisher can access these mechanisms. Such an interface can comprise a predictive analysis based on information gathered from the publisher's web sites, that can enable the publisher to visualize the effect of these mechanisms on factors such as ad-generated revenue and visitor return rates.

Abstract: Determining the probability that a user or program fraudulently initiated a web-page request is described herein. A data-mining component is configured to determine attributes associated with the web-page request. A computation component is configured to calculate a probability that the web-page request was fraudulently initiated. To calculate this probability, the attributes and other parameters are fed into a statistical model. An auction component is configured to locate one or more advertisements to display on the web page based on the probability. The auction component may also be configured to restrict the advertisements for display based on advertiser-specified target criteria.