Personalized Advertisement Recommendations Using Implicit Feedback

Abstract

Online advertising is a big part of everyday life for the average internet user, and an important source of income for most mass media companies. Studies have shown that users often prefer ads that are relevant to their interests, and that users that have a positive opinion towards advertisements are less likely to use ad blockers. It is therefore beneficial for companies to personalize advertising, not only because it can increase their revenue, but also to prevent users from turning to ad blockers. Displaying personalized advertisements can be done through the use of collaborative filtering, which is a popular technique in recommender systems. In the context of advertising, collaborative filtering models can recommend an ad to a user by identifying other users with similar preferences, and then choosing an ad that they have liked. The challenge in this scenario is that users don’t explicitly express which ads they like and which they dislike. Users may instead click on ads, thereby implicitly indicating their preferences. This type of implicit feedback does however raise several challenges. One of the central challenges is how to interpret the lack of negative feedback, i.e. the events where a user has seen an ad without clicking on it. Does zero clicks mean that the user disliked the ad, is indifferent, or did they simply not notice it? This master’s thesis aims to address the challenges posed by implicit feedback data, with the primary goal being to improve personalized online advertising. The research consists of two main experiments based on industry data provided by Amedia, one of the largest media companies in Norway. I propose three novel approaches to infer user preferences towards advertisements, alongside three approaches that are more traditional. By inferring user preferences, it becomes possible to employ collaborative filtering methods such as matrix factorization for generating advertisement recommendations. Three different matrix factorization models were chosen for this task. Through a comprehensive offline evaluation, a comparative analysis was conducted in order to uncover which of the scoring approaches resulted in the highest quality advertisement recommendations across several performance metrics. The findings from the experiments suggest that the proposed novel approaches were generally superior at representing user preferences compared to the more traditional approaches. Overall, the research conducted in this thesis addresses some of the challenges with using implicit feedback data for personalization, and proposes how this topic can be further explored in order to improve personalized advertising.