MSCS Seminar - Daniel Kluver

4:40 PM  - 5:40 PM
Tuesday Feb 13, 2018
Olin-Rice Science Center 250

Learning What You Want: Understanding and Improving Rating Interfaces for Online Recommender Systems

User-provided rating data is an important part of how people evaluate goods online. People commonly use average ratings to decide if a product is worth buying, or a movie is worth watching. Recommender systems, such as Amazon and Netflix, go beyond average rating, using machine learning algorithms to make personal recommendations for each user. There are many algorithms for recommendation, each with different strengths and weaknesses. However, they all have one thing in common: good recommendations require good user ratings. Many different interfaces for collecting ratings exist and it can be hard to know which one will provide the best data for a given system. In this talk I will present my research into ways to measure the amount of information about user preferences a system collects from different interfaces.

Contact: sburr

This event is for: Students and Faculty

Sponsored By: Mathematics, Statistics, and Computer Science

Categories: Front Page Events and Lectures and Speakers