Decision-Theoretic Bidding Based on Learned Density Models in Simultaneous, Interacting Auctions

TL;DR

This paper introduces a decision-theoretic bidding approach for simultaneous, interacting auctions that leverages learned density models to optimize bids, demonstrated through a competitive autonomous agent in a trading competition.

Contribution

It presents a novel boosting-based algorithm for conditional density estimation and integrates it into an autonomous bidding agent for multiple interacting auctions.

Findings

Boosting-based density estimation outperforms alternatives.

The ATTac-2001 agent achieved top performance in TAC-01.

Effective price prediction improves bidding strategies.

Abstract

Auctions are becoming an increasingly popular method for transacting business, especially over the Internet. This article presents a general approach to building autonomous bidding agents to bid in multiple simultaneous auctions for interacting goods. A core component of our approach learns a model of the empirical price dynamics based on past data and uses the model to analytically calculate, to the greatest extent possible, optimal bids. We introduce a new and general boosting-based algorithm for conditional density estimation problems of this kind, i.e., supervised learning problems in which the goal is to estimate the entire conditional distribution of the real-valued label. This approach is fully implemented as ATTac-2001, a top-scoring agent in the second Trading Agent Competition (TAC-01). We present experiments demonstrating the effectiveness of our boosting-based price predictor relative to several reasonable alternatives.