GTLGJan 16, 2014

RoxyBot-06: Stochastic Prediction and Optimization in TAC Travel

arXiv:1401.3829v112 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of designing effective trading agents for competitive auction-based markets, though it appears incremental as it builds on existing prediction-optimization frameworks.

The paper tackled the problem of autonomous bidding in the Trading Agent Competition's travel division by developing RoxyBot, which uses stochastic price prediction and optimization to win the 2006 competition in a close finish.

In this paper, we describe our autonomous bidding agent, RoxyBot, who emerged victorious in the travel division of the 2006 Trading Agent Competition in a photo finish. At a high level, the design of many successful trading agents can be summarized as follows: (i) price prediction: build a model of market prices; and (ii) optimization: solve for an approximately optimal set of bids, given this model. To predict, RoxyBot builds a stochastic model of market prices by simulating simultaneous ascending auctions. To optimize, RoxyBot relies on the sample average approximation method, a stochastic optimization technique.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes