Evimaria Terzi wins NSF Early Career Award

Evimaria Terzi has won an NSF Faculty Early Career Development Award to
support her research and teaching efforts in data mining, in particular
her project “On the identification of collections with complex

Evimaria’s Project Abstract:
“In the classical COLLECTION problem, arising in recommendation systems
for products, services and people, the input consists of a pool of
entities (e.g., movies, books, experts) and an objective function and the
goal is to identify a collection (i.e., a subset) of entities from the
pool that optimizes the objective function. For example, in
movie-recommendation systems (e.g., Netflix) the goal is to identify
subsets of movies to recommend to registered users. Similarly,
review-management systems (e.g., Amazon, Yelp) process thousands of
reviews about a product and need to identify a small subset of them, which
the users can read in order to make purchase decisions. Analogous problems
arise in social networks and social media (e.g., Twitter, Facebook), where
advertisers need to identify a small set of target nodes for their
campaigns so that their product spreads as much as possible. Finally,
Human Resources (HR) departments of companies often use
expertise-management systems (e.g., LinkedIn, odesk) in order to identify
the subset of experts that are the most appropriate to complete a specific

Despite their usefulness, existing instantiations of the COLLECTION
problem have the following two shortcomings: (a) they fail to take into
consideration the need for sequential collections and (b) they do not
consider the rationality of the entities that are called upon to form the
collections. This project addresses these two shortcomings by designing
methods that (a)identify sequences of collections, rather than a single
collection and (b) identify collections of rational entities with personal
objectives. This research provides to formal definitions of such
sequential and rationality-aware recommendations and focuses on the design
algorithms for such problems, as they arise in applications like
recommendation systems, social networks or expertise-management systems.
Apart from algorithm design it also builds domain-specific testbed
applications, which implement these methods and make them accessible to
the general public. The models and methods produced by this research
provide new direction in the areas of recommendation systems with
applications to online applications including social-network sites (e.g.,
LinkedIn, Facebook, etc.), online recommendation systems (e.g., Amazon,
Netflix, etc.) and daily-deal sites (e.g., Groupon, LivingSocial, etc.).”

About the award, according to the NSF website:
“The Faculty Early Career Development (CAREER) Program is a
Foundation-wide activity that offers the National Science Foundation’s
most prestigious awards in support of the early career-development
activities of those teacher-scholars who most effectively integrate
research and education within the context of the mission of their
organization. Such activities should build a firm foundation for a
lifetime of integrated contributions to research and education.”

Congratulations to Evimaria!

View all posts