Hands on Data and Algorithmic Bias in Recommender Systems
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore data and algorithmic bias in recommender systems through this comprehensive tutorial from the UMAP'20 conference. Delve into real-world examples across various domains to understand the problem space and key concepts of bias investigation in recommendation. Engage with two practical use cases addressing biases that lead to disparate item exposure based on popularity and systematic discrimination against protected user classes. Learn a range of techniques for evaluating and mitigating bias impact on recommended lists, including pre-, in-, and post-processing procedures. Gain hands-on experience with accompanying Jupyter notebooks that apply core concepts to data from real-world platforms. This 2-hour 37-minute session, led by Ludovico Boratto and Mirko Marras, provides valuable insights for both researchers and practitioners interested in fairness and bias mitigation in recommender systems.
Syllabus
Hands on Data and Algorithmic Bias in Recommender Systems
Taught by
ACM SIGCHI
Related Courses
Introduction to Recommender SystemsUniversity of Minnesota via Coursera Text Retrieval and Search Engines
University of Illinois at Urbana-Champaign via Coursera Machine Learning: Recommender Systems & Dimensionality Reduction
University of Washington via Coursera Java Programming: Build a Recommendation System
Duke University via Coursera Introduction to Recommender Systems: Non-Personalized and Content-Based
University of Minnesota via Coursera