Competing AI: How does competition feedback affect machine learning?

Abstract

This papers studies how competition affects machine learning (ML) predictors. As ML becomes more ubiquitous, it is often deployed by companies to compete over customers. For example, digital platforms like Yelp use ML to predict user preference and make recommendations. A service that is more often queried by users, perhaps because it more accurately anticipates user preferences, is also more likely to obtain additional user data (e.g. in the form of a Yelp review). Thus, competing predictors cause feedback loops whereby a predictor's performance impacts what training data it receives and biases its predictions over time. We introduce a flexible model of competing ML predictors that enables both rapid experimentation and theoretical tractability. We show with empirical and mathematical analysis that competition causes predictors to specialize for specific sub-populations at the cost of worse performance over the general population. We further analyze the impact of predictor specialization on the overall prediction quality experienced by users. We show that having too few or too many competing predictors in a market can hurt the overall prediction quality. Our theory is complemented by experiments on several real datasets using popular learning algorithms, such as neural networks and nearest neighbor methods.

arXiv commentAccepted to AISTATS 2021

References in corpus (15)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• The NumPy array: a structure for efficient numerical computation
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Popular Ensemble Methods: An Empirical Study
• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
• Counterfactual Multi-Agent Policy Gradients
• Emergent Tool Use From Multi-Agent Autocurricula
• Thermodynamics as a theory of decision-making with information processing costs
• Emergent Complexity via Multi-Agent Competition
• Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization
• Deconvolving Feedback Loops in Recommender Systems
• Are sample means in multi-armed bandits positively or negatively biased?
• Why Adaptively Collected Data Have Negative Bias and How to Correct for It
• Competing Bandits: Learning under Competition
• Equilibrium Characterization for Data Acquisition Games