======================= CALL FOR PARTICIPATION ======================= FDMA 2012: International Workshop on Fraud Detection in Mobile Advertising, Singapore Management University, Singapore, 4 November 2012 (in conjunction with the Asian Conference on Machine Learning 2012) Website: http://palanteer.sis.smu.edu.sg/fdma2012/ Important Dates --------------- August 15 – Registration opens September 1 – Competition begins September 30 – Competition ends October 7 – Winners notified October 21 – Workshop paper submission November 4 – Workshop Introduction ------------ Online advertising flourishes as the ideal choice for both small and large businesses to target their marketing campaigns to the appropriate customers on the fly. An advertiser provides an advertising commissioner with its advertisements, plans a budget, and sets a commission for each customer action. The content publishers, on the other hand, make a contract with the commissioner to display advertisements on their websites. However, since publishers earn revenue based on impressions and clicks they drive to advertisers, there is an incentive for dishonest publishers to inflate the number of impressions/clicks their sites generate—a phenomenon known as click fraud. Click fraud hinders the reliability of online advertising system, and the market for online advertising will eventually contract in a long-term. Moreover, it may lead to expensive litigations from unsatisfied advertisers and bad reputation for the commissioner. It is important for the commissioner to proactively prevent click fraud so as to convince their advertisers the fairness of their accounting practices. Accordingly, a reliable click fraud detection system is needed to help identify dishonest publishers and maintain the commissioner’s credibility. Workshop -------- A workshop for the competition results will be held at the Asian Conference on Machine Learning (ACML) 2012 - http://acml12.comp.nus.edu.sg/ Prize ----- The primary entries from all participants will be ranked in decreasing order of their respective evaluation scores, computed on the test set. The top three ranks will receive the following cash prizes: * 1st place - SGD 4,000 * 2nd place - SGD 2,000 * 3rd place - SGD 1,000 Publication ----------- The best entries of the data mining competition will be assembled for a jointly submitted article to Journal of Machine Learning Research (JMLR). Organizers ---------- Program Chairs: * Ee-Peng LIM, Singapore Management University * Richard J. OENTARYO, Singapore Management University * Feida ZHU, Singapore Management University * David LO, Singapore Management University * Kok Fung LAI, BuzzCity Pte. Ltd. Web Administrators: * Juan DU, Singapore Management University * Philips K. PRASETYO, Singapore Management University Dataset --------- This competition involves advertisement data provided by BuzzCity Pte. Ltd. BuzzCity is a global mobile advertising network that has millions of consumers around the world on mobile phones and devices. In Q1 2012, over 45 billion ad banners were delivered across the BuzzCity network consisting of more than 10,000 publisher sites which reach an average of over 300 million unique users per month. The number of smartphones active on the network has also grown significantly, accounting for more than 32% phones that are served advertisements across the BuzzCity network. The “raw” data used in this competition consist of two major types: publisher data and click data; the former records the publisher’s account profile, while the latter records the click traffics associated with the publishers. Task ----- The goal of this competition is to build an effective data-drive models for proactive detection of fraudulent publishers. There are three types of publisher's status/label, as follows: * “OK” - Publishers whom BuzzCity deems as having healthy traffic, or those who slipped their detection mechanisms. * “Observation” – Publishers who may have just started their traffic or their traffic statistics deviates from system wide average. BuzzCity does not have any conclusive stand with these publishers yet. * “Fraud” – Publishers who are deemed as fraudulent with clear proof. Buzzcity suspends their accounts and their earnings will not be paid. Accordingly, the main task of this competition is to distinguish the "Fraud" publishers from the "OK" and "Observation" publishers, based on their click traffic and account profiles. This classification will help BuzzCity identify fraudulent publishers and understand the underlying fraud mechanisms. Submission ---------- You may participate in the competition as an individual or as part of a team of up to five participants. Only two submissions per day from each team are allowed. You may only be involved in one "team" in the competition (i.e. either as an individual or as a member of a single team, but not both). For team registrations, the team must select a team leader, who will provide the team name, and the names, email addresses and affiliations of all members during registration. Team members are required to register for a user account and log into the competition site. The names and e-mail addresses of team members will not be publicly displayed during the competition. If you are an individual winner or member of a winning team, your name will be announced following the competition. Contacts -------- * Richard J. OENTARYO (Program Chair) Email: roentaryo@smu.edu.sg * Juan DU (Web Administrator) Email: juandu@smu.edu.sg