With the rapid growth of the Internet, online advertisement plays a more and more important role in the advertising market and has become a billion-dollar business ($19.5 billon in 2007). One of the current and widely used revenue models for online advertising is Pay-per-click (PPC), which involves charging for each click based on the popularity of keywords and the number of competing advertisers. However, the pay-per-click model leaves room for individuals or rival companies to generate false clicks (i.e., click fraud) due to the lack of verifiable engagement in PPC requests. It has been reported that in online ad market, 14.6% are paid to Click Fraud, which has damaged the development and healthiness of online advertising. This project is (1) developing a fundamentally new framework for verifiable clicks and a new way of defining the quality of clicks; and (2) developing filtering-based tools for validating and weeding out suspicious clicks, each of which provides quantifiable guarantees on false positive and negative rates while involving a reasonable processing overhead and space requirements. The new framework promotes transparency and trust between advertisers and online ad businesses and eliminates the need for keeping ?click filters? as trade secrets. A set of portable course materials is also being developed to facilitate the teaching of developed techniques in undergraduate and graduate courses. Some of these results are planned to be licensed for use by online ad businesses.
CT-ER: Detecting Click Fraud in Pay-Per-Click Streams of Online Advertising Networks