Collective Altruism in Recommender Systems
From Data Skeptic by Kyle Polich
February 27, 2026 · 55 min
About this episode
This episode discusses strategic learning in recommender systems with a focus on collective user behavior and its implications for algorithm performance.
Ekaterina (Kat) Fedorova from MIT EECS joins us to discuss strategic learning in recommender systems—what happens when users collectively coordinate to game recommendation algorithms. Kat's research reveals surprising findings: algorithmic "protest movements" can paradoxically help platforms by providing clearer preference signals, and the challenge of distinguishing coordinated behavior from bot activity is more complex than it appears. This episode explores the intersection of machine learning and game theory, examining what happens when your training data actively responds to your algorithm.
People in this episode
Host: Kyle Polich
Guest: Ekaterina (Kat) Fedorova
Topics covered
- recommender systems
- strategic learning
- algorithmic behavior
- machine learning
- game theory
Keywords
- recommender systems
- strategic learning
- algorithmic protest
- machine learning
- game theory
- user behavior
- preference signals
Mentioned in this episode
Organizations: MIT EECS
More episodes of Data Skeptic
- Student Spotlight: Aaron Payne, Data Analyst · May 1, 2026 · 26 min
- The Future is Agentic in Recommender Systems · April 25, 2026 · 49 min
- Book Ratings and Recommendations · March 27, 2026 · 39 min
- Disentanglement and Interpretability in Recommender Systems · March 10, 2026 · 31 min
- Niche vs Mainstream · February 18, 2026 · 34 min
- Healthy Friction in Job Recommender Systems · February 2, 2026 · 27 min
Explore listener stats, chart rankings, contacts and more on the Data Skeptic podcast page.