Modern recommender systems: matrices, bandits, and neurons

Speaker:  Georgia Koutrika – Athens, Greece
Topic(s):  Information Systems, Search, Information Retrieval, Database Systems, Data Mining, Data Science

Abstract

The proliferation of digital content in a plurality of forms (including e-news, movies, and online courses), along with the popularity of portable devices has created immense opportunities as well as challenges for systems to provide users with information and services that best serve the users' needs. Recommender systems come to the rescue providing advice on movies, products, travel, leisure activities, and many other topics, and have become very popular in systems, such as Netflix, Amazon, Quora, and Yelp. Recent years have witnessed an explosion in methods applied to solve the recommendation problem and modern recommender systems have become increasingly more complex departing from their early content-based and collaborative filtering versions. In this talk, we will take a look at three of the most prominent categories of recommendations methods used in systems these days: matrix factorization, multi-armed bandits and deep learning approaches.

About this Lecture

Number of Slides:  160
Duration:  180 minutes
Languages Available:  English, Greek
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.