Auction Design with Data-Driven Misspecifications

TL;DR

This paper models auction environments where novice bidders use data-driven methods to estimate their values, revealing inefficiencies in classical auction formats due to correlation and information restrictions.

Contribution

It introduces a model of data-driven novice bidders with private signals, analyzing their behavior and inefficiencies in classical and auction-like mechanisms.

Findings

Data-driven bidders may behave suboptimally in classical auctions with correlated signals.

Mixing rational and novice bidders leads to auction inefficiencies.

Inefficiencies extend to all one-dimensional bid mechanisms.

Abstract

We consider auction environments in which at the time of the auction bidders observe signals about their ex-post value. We introduce a model of novice bidders who do not know know the joint distribution of signals and instead build a statistical model relating others' bids to their own ex post value from the data sets accessible from past similar auctions. Crucially, we assume that only ex post values and bids are accessible while signals observed by bidders in past auctions remain private. We consider steady-states in such environments, and importantly we allow for correlation in the signal distribution. We first observe that data-driven bidders may behave suboptimally in classical auctions such as the second-price or first-price auctions whenever there are correlations. Allowing for a mix of rational (or experienced) and data-driven (novice) bidders results in inefficiencies in such auctions, and we show the inefficiency extends to all auction-like mechanisms in which bidders are restricted to submit one-dimensional (real-valued) bids.