Brendan Kitts

Cross-sell: a fast promotion-tunable customer-item recommendation method based on conditionally independent probabilities

We develop a method for recommending products to customers with applications to both on-line and surface mail promotional offers. Our method differs from previous work in collaborative filtering [8] and imputation [18], in that we assume probabilities are conditionally independent. This assumption, which is also made in Naive Bayes [5], enables us to pre-compute probabilities and store them in main memory, enabling very fast performance on millions of customers. The algorithm supports a variety of tunable parameters so that the method can address different promotional objectives. We tested the algorithm at an on-line hardware retailer, with 17,400 customers divided randomly into control and experimental groups. In the experimental group, clickthrough increased by +40% (p<0.01), revenue by +38% (p<0.07), and units sold by +61% (p<0.01). By changing the algorithm’s parameter settings we found that these results could be improved even further. This work demonstrates the considerable potential of automated data mining for dramatically increasing the profitability of on and off-line retail promotions.

Introduction to the special issue on successful real-world data mining applications

Since its inception, the field of Data Mining and Knowledge Discovery from Databases has been driven by the need to solve practical problems [4]. From scaling to large databases and handling noisy and high-dimensional data to finding associational patterns in grocery store transaction data, data mining is a research area rich in application [1]. Despite its practical roots few case studies of data mining applications have been published. The industrial track of the annual SIGKDD conference has provided one such forum, but rarely do these papers present complete descriptions of deployed systems [2]. This special issue attempts to address the gap by showcasing the choices, strategies, and lessons learned from building a real-world data mining application. In a sense this collection is a follow-up to the first workshop on data mining case studies held during ICDM-2006 [3]. This issue however introduces several new papers. Of the 29 papers reviewed 10 papers were accepted. The papers come from a broad range of application areas including Customer Relationship Management, Medicine, Taxation, and Software Development.

The Components and Impact of Sponsored Search

Sponsored search has dramatically influenced how people interact with the Web. It has funded the Web searching infrastructure that users have grown accustomed to and provided unparalleled reach, frequency, and control of marketing efforts and advertising campaigns. Sponsored search advertising has dramatically impacted search engines, consumers, and organizations, and will continue to do so in the foreseeable future.

Click Fraud Detection: Adversarial Pattern Recognition over 5 Years at Microsoft

Microsoft adCenter is the third largest Search advertising platform in the United States behind Google and Yahoo, and services about 10 % of US traffic. At this scale of traffic approximately 1 billion events per hour, amounting to 2.3 billion ad dollars annually, need to be scored to determine if it is fraudulent or bot-generated [32, 37, 41]. In order to accomplish this, adCenter has developed arguably one of the largest data mining systems in the world to score traffic quality, and has employed them successfully over 5 years. The current paper describes the unique challenges posed by data mining at massive scale, the design choices and rationale behind the technologies to address the problem, and shows some examples and some quantitative results on the effectiveness of the system in combating click fraud.

Attribution of Conversion Events to Multi-channel Media

This paper presents a practical method for measuring the impact of multiple marketing events on sales, including marketing events that are not traditionally trackable. The technique infers which of several competing media events are likely to have caused a given conversion. We test the method using hold-out sets, and also a live media experiment in which we test whether the method can accurately predict television-generated web conversions.

Click Fraud Detection with Bot Signatures

Click Fraud Bots pose a significant threat to the online economy. To-date efforts to filter bots have been geared towards identifiable useragent strings, as epitomized by the IABs Robots and Spiders list. However bots designed to perpetrate malicious activity or fraud, are designed to avoid detection with these kinds of lists, and many use very sophisticated schemes for cloaking their activities. In order to combat this emerging threat, we propose the creation of Bot Signatures for training and evaluation of candidate Click Fraud Detection Systems. Bot signatures comprise keyed records connected to case examples. We demonstrate the technique by developing 8 simulated examples of Bots described in the literature including Click Bot A.

Targeting Television Audiences Using Demographic Similarity

Targeting advertising on television is difficult due to limitations around ad tracking and ad delivery. This paper describes a new method of television advertising which can work with today’s state of the art broadcast television media. The method works by calculating a match score between historical buyer demographics and television station-program-day-hour demographics. Television media which is very similar to the demographic of the buyer is targeted for advertising. The method is tested in a live media buy and it is shown that the method can significantly increases the performance of television advertising.

Can Television Advertising Impact Be Measured on the Web? Web Spike Response as a Possible Conversion Tracking System for Television

Consumers are increasingly using internet-connected devices while watching television. This paper will show that it is possible to measure web activity bursts that peak about 13 seconds after the end of traditional TV ad broadcasts. By measuring this effect, we propose that it may be possible to deploy a web-based TV conversion tracking system that will work on TV systems.

A High-Dimensional Set Top Box Ad Targeting Algorithm Including Experimental Comparisons to Traditional TV Algorithms

We present a method for targeting ads on television that works on todays TV systems. The method works by mining vast amounts of Set Top Box data, as well as advertiser customer data. From both sources the system builds demographic profiles, and then looks for media that have the highest match per dollar to the customer profile. The method was tested in four live television campaigns, comprising over 22,000 airings, and we present experimental results.

Click fraud botnet detection by calculating mix adjusted traffic value: A method for de-cloaking click fraud attacks that is resistant to spoofing

Click Fraud remains one of the most durable fraudulent schemes online. With 50 billion dollars being generated per year by Google alone, a fraudulent publisher is able to capture a significant amount of revenue with a small investment. The most well heeled click fraud attacks employ large distributed botnets, deceptive publisher pages, malware infection, and fake conversion “chaff” in an attempt to cloak fraudulent activity. We describe an algorithm that we call Mix Adjustment which corrects for traffic bias differences. The method is scalable and we show a simple implementation that can be applied to current weblog processing systems. We show two case studies of this algorithm on real fraud detection problems: (a) WOW Bot net detection, (b) Advertiser fraud detection.