Self-Confirming Price Prediction for Bidding in Simultaneous Ascending Auctions

TL;DR

This paper introduces a new decision-theoretic bidding strategy for simultaneous ascending auctions that uses self-confirming price predictions, addressing the exposure problem and showing promising experimental results.

Contribution

It proposes a novel family of bidding strategies based on self-confirming price distributions, filling a gap in auction theory for handling the exposure problem.

Findings

Self-confirming price predictions are correct when all agents use them.

Bidding strategies based on these predictions are effective in experiments.

The approach offers a practical method for agents to mitigate risks in simultaneous auctions.

Abstract

Simultaneous ascending auctions present agents with the exposure problem: bidding to acquire a bundle risks the possibility of obtaining an undesired subset of the goods. Auction theory provides little guidance for dealing with this problem. We present a new family of decisiontheoretic bidding strategies that use probabilistic predictions of final prices. We focus on selfconfirming price distribution predictions, which by definition turn out to be correct when all agents bid decision-theoretically based on them. Bidding based on these is provably not optimal in general, but our experimental evidence indicates the strategy can be quite effective compared to other known methods.