Modeling Auction Price Uncertainty Using Boosting-Based Conditional Density Estimation

Abstract

In complicated, interacting auctions, a fundamental problem is the prediction of prices of goods in the auctions, and more broadly, the modeling of uncertainty regarding these prices. In this paper, we present a machine-learning approach to this problem. The technique is based on a new and general boosting-based algorithm for conditional density estimation problems of this kind. This algorithm, which we present in detail, is at the heart of ATTac-2001, a top-scoring agent in the recent Trading Agent Competition (TAC-01). We describe how ATTac-2001 works, the results of the competition, and controlled experiments evaluating the effectiveness of price prediction in auctions.

Cite

Text

Schapire et al. "Modeling Auction Price Uncertainty Using Boosting-Based Conditional Density Estimation." International Conference on Machine Learning, 2002.

Markdown

[Schapire et al. "Modeling Auction Price Uncertainty Using Boosting-Based Conditional Density Estimation." International Conference on Machine Learning, 2002.](https://mlanthology.org/icml/2002/schapire2002icml-modeling/)

BibTeX

@inproceedings{schapire2002icml-modeling,
  title     = {{Modeling Auction Price Uncertainty Using Boosting-Based Conditional Density Estimation}},
  author    = {Schapire, Robert E. and Stone, Peter and McAllester, David A. and Littman, Michael L. and Csirik, János A.},
  booktitle = {International Conference on Machine Learning},
  year      = {2002},
  pages     = {546-553},
  url       = {https://mlanthology.org/icml/2002/schapire2002icml-modeling/}
}