Martino Banchio
Martino Banchio
Research Interests
- Microeconomic Theory
- Market Design
- Computer Science
- Industrial Organization
Job Market Paper
(with G. Mantegazza) We develop a theoretical model to study strategic interactions between adaptive learning algorithms. Applying continuous-time techniques, we uncover the mechanism responsible for collusion between Artificial Intelligence algorithms documented by recent experimental evidence. We show that spontaneous coupling between the algorithms' estimates leads to periodic coordination on actions that are more profitable than static Nash equilibria. We provide a sufficient condition under which this coupling is guaranteed to disappear, and algorithms learn to play undominated strategies. We apply our results to interpret and complement experimental findings in the literature, and to the design of learning-robust strategy-proof mechanisms. We show that ex-post feedback provision guarantees robustness to the presence of learning agents. We fully characterize the optimal learning-robust mechanisms: they are menu mechanisms.
Working Papers
(with A. Skrzypacz) Motivated by online advertising auctions, we study auction design in repeated auctions played by simple Artificial Intelligence algorithms (Q-learning). We find that first-price auctions with no additional feedback lead to tacit-collusive outcomes (bids lower than values), while second-price auctions do not. We show that the difference is driven by the incentive in first-price auctions to outbid opponents by just one bid increment. This facilitates re-coordination on low bids after a phase of experimentation. We also show that providing information about the lowest bid to win, as introduced by Google at the time of the switch to first-price auctions, increases the competitiveness of auctions.
(with F. Yang) A monopolist wants to sell one item per period to a consumer with evolving and persistent private information. The seller sets a price each period depending on the history so far, but cannot commit to future prices. We show that, regardless of the degree of persistence, any equilibrium under a D1-style refinement gives the seller revenue no higher than what she would get from posting all prices in advance.
(with E. Munro) We study the problem of a planner who wants to reduce inequality by awarding prizes to the worst contestants in a tournament without incentivizing shirking. We prove that no ex-post targeting mechanism eliminates perverse incentives and show that the optimal dynamic rule is computationally infeasible. We design an approximately optimal, incentive-compatible mechanism that targets low-ranked contestants based on the tournament's history up to an endogenous stopping time. We describe applications to eligibility for remedial education, retraining benefits for the unemployed, and draft lotteries in sports. Using data from the NBA, we show how our mechanism aligns incentives and improves targeting.