When the Umpire is also a Player - Bias in Private Label Product Recommendations on E-commerce Marketplaces
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore the potential biases in private label product recommendations on e-commerce platforms through this 21-minute conference talk from FAccT 2021. Delve into the research conducted by A. Dash, A. Chakraborty, S. Ghosh, A. Mukherjee, and K. Gummadi, examining the dual role of e-commerce platforms as both marketplace operators and product sellers. Investigate the algorithms used, new concerns arising from this conflict of interest, and the data collection methods employed. Analyze key findings related to exposure bias and biases in sponsored recommendations, gaining insights into the implications for fair competition and consumer choice in online marketplaces.
Syllabus
Introduction
Background
Algorithms
New Concern
Data Collection
Findings
Exposure Bias
Biases in Sponsored Recommendations
Conclusion
Taught by
ACM FAccT Conference
Related Courses
A Bayesian Model of Cash Bail DecisionsAssociation for Computing Machinery (ACM) via YouTube A Pilot Study in Surveying Clinical Judgments to Evaluate Radiology Report Generation
Association for Computing Machinery (ACM) via YouTube A Review of Taxonomies of Explainable Artificial Intelligence - XAI Methods
Association for Computing Machinery (ACM) via YouTube A Semiotics-Based Epistemic Tool to Reason About Ethical Issues in Digital Technology Design and Development
Association for Computing Machinery (ACM) via YouTube A Statistical Test for Probabilistic Fairness
Association for Computing Machinery (ACM) via YouTube