Self-confirming price-prediction strategies for simultaneous one-shot auctions

Bidding in simultaneous auctions is challenging because an agent's value for a good in one auction may depend on the outcome of other auctions; that is, bidders face an exposure problem. Previous works have tackled the exposure problem with heuristic strategies that employ probabilistic price predictions—so-called price-prediction strategies. We introduce a concept of self-confirming prices, and show that within an independent private value model, Bayes–Nash equilibrium can be fully characterized as a profile of optimal price-prediction strategies with self-confirming prices. We operationalize this observation by exhibiting a practical procedure to compute near-self-confirming price predictions given a price-prediction strategy. An extensive empirical game-theoretic analysis demonstrates that bidding strategies that use such predictions are effective in simultaneous auctions with both complementary and substitutable preference structures. In particular, we produce one such strategy that finds near-optimal bids, thereby outperforming all previously studied bidding heuristics in these environments.