MP Wellman, DM Reeves, KM Lochner, and Y Vorobeychik

Journal of Artificial Intelligence Research 21:19–36, 2004.
Copyright (c) 2004, AI Access Foundation.


The 2002 Trading Agent Competition (TAC) presented agents with a challenging market game in the domain of travel shopping. One of the pivotal issues in this domain is uncertainty about hotel prices, which have a significant influence on the relative cost of alternative trip schedules. Thus, virtually all participating agents employ some method for predicting hotel prices. We survey approaches employed in the tournament, finding that agents apply an interesting diversity of techniques, taking into account differing sources of evidence bearing on prices. Based on data provided by entrants on their agents’ actual predictions in the TAC-02 finals and semifinals, we analyze the relative efficacy of these approaches. Employing a new measure of prediction quality, we relate absolute accuracy to bottom-line performance in the game.