Detecting Click Fraud in Online Advertising: A Data Mining Approach

1643

收藏 2015-02-10

[size=19.9253px]A
[size=16.6043px]Click fraud{the deliberate clicking on advertisements with no real interest on the productor service oered{is one of the most daunting problems in online advertising. Building an eective fraud detection method is thus pivotal for online advertising businesses.we organized aFraud Detection in Mobile Advertising(FDMA) 2012 Competition, openingthe opportunity for participants to work on real-world fraud data from BuzzCity Pte.Ltd., a global mobile advertising company based in Singapore. In particular, the task is to identify fraudulent publishers who generate illegitimate clicks, and distinguish them from normal publishers. The competition was held from September 1 to September 30,2012, attracting 127 teams from more than 15 countries. The mobile advertising data are unique and complex, involving heterogeneous information, noisy patterns with miss-ing values, and highly imbalanced class distribution. The competition results provide a comprehensive study on the usability of data mining-based fraud detection approaches in practical setting. Our principal ndings are that features derived from ne-grained time-series analysis are crucial for accurate fraud detection, and that ensemble methods oerpromising solutions to highly-imbalanced nonlinear classication tasks with mixed vari-able types and noisy/missing patterns. The competition data remain available for further studies at[size=16.6043px]http://palanteer.sis.smu.edu.sg/fdma2012/