Nadav Golbandi

On bootstrapping recommender systems

Recommender systems perform much better on users for which they have more information. This gives rise to a problem of satisfying users new to a system. The problem is even more acute considering that some of these hard to profile new users judge the unfamiliar system by its ability to immediately provide them with satisfying recommendations, and may be the quickest to abandon the system when disappointed. Rapid profiling of new users is often achieved through a bootstrapping process - a kind of an initial interview - that elicits users to provide their opinions on certain carefully chosen items or categories. This work offers a new bootstrapping method, which is based on a concrete optimization goal, thereby handily outperforming known approaches in our tests.

Expediting search trend detection via prediction of query counts

The massive volume of queries submitted to major Web search engines reflects human interest at a global scale. While the popularity of many search queries is stable over time or fluctuates with periodic regularity, some queries experience a sudden and ephemeral rise in popularity that is unexplained by their past volumes. Typically the popularity surge is precipitated by some real-life event in the news cycle. Such queries form what are known as search trends. All major search engines, using query log analysis and other signals, invest in detecting such trends. The goal is to surface trends accurately, with low latency relative to the actual event that sparked the trend. This work formally defines precision, recall and latency metrics related to top-k search trend detection. Then, observing that many trend detection algorithms rely on query counts, we develop a linear auto-regression model to predict future query counts. Subsequently, we tap the predicted counts to expedite search trend detection by plugging them into an existing trend detection scheme. Experimenting with query logs from a major Web search engine, we report both the stand-alone accuracy of our query count predictions, as well as the task-oriented effects of the prediction on the emitted trends. We show an average reduction in trend detection latency of roughly twenty minutes, with a negligible impact on the precision and recall metrics.

Budget-Constrained Item Cold-Start Handling in Collaborative Filtering Recommenders via Optimal Design

It is well known that collaborative filtering (CF) based recommender systems provide better modeling of users and items associated with considerable rating history. The lack of historical ratings results in the user and the item cold-start problems. The latter is the main focus of this work. Most of the current literature addresses this problem by integrating content-based recommendation techniques to model the new item. However, in many cases such content is not available, and the question arises is whether this problem can be mitigated using CF techniques only. We formalize this problem as an optimization problem: given a new item, a pool of available users, and a budget constraint, select which users to assign with the task of rating the new item in order to minimize the prediction error of our model. We show that the objective function is monotone-supermodular, and propose efficient optimal design based algorithms that attain an approximation to its optimum. Our findings are verified by an empirical study using the Netflix dataset, where the proposed algorithms outperform several baselines for the problem at hand.

Engagement-based user attention distribution on web article pages

The main monetization vehicle of many Web media sites are display ads located on article pages. Those ads are typically displayed either as banners on top of the page, or on the pages side bar. Advertiser ROI depends on the quality of ad targeting, as well as on how noticeable those ads are to users reading the article. Focusing on the latter issue, previous work has studied which ad positions are, on aggregate, more noticed by users. This work takes the first step toward the personalized positioning of ads on article pages. We demonstrate a correlation between the level of attention that users devote to a story, and the position of the most noticeable graphic element on the side bar. In particular, we find that the graphic element most noticed by a user is roughly to the side of the point in the article where the users attention waned. We argue that this finding lays the foundation for increasing display advertising effectiveness by tailoring ad positions on each article page impression to the user viewing it.

Hierarchical composable optimization of web pages

The process of creating modern Web media experiences is challenged by the need to adapt the content and presentation choices to dynamic real-time fluctuations of user interest across multiple audiences. We introduce FAME -- a Framework for Agile Media Experiences -- which addresses this scalability problem. FAME allows media creators to define abstract page models that are subsequently transformed into real experiences through algorithmic experimentation. FAMEs page models are hierarchically composed of simple building blocks, mirroring the structure of most Web pages. They are resolved into concrete page instances by pluggable algorithms which optimize the pages for specific business goals. Our framework allows retrieving dynamic content from multiple sources, defining the experimentations degrees of freedom, and constraining the algorithmic choices. It offers an effective separation of concerns in the media creation process, enabling multiple stakeholders with profoundly different skills to apply their crafts and perform their duties independently, composing and reusing each others work in modular ways.