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

T oyota T e hnolo gi al Institute at Chi ago 1427 East 60th Str e et, Chi ago IL, 60637 USA Abstra t Au tions are b e oming an in reasingly p opular metho d for transa ting business, esp e-ially o v er the In ternet. This arti le presen ts a general approa h to building autonomous bidding agen ts to bid in m ultiple sim ultaneous au tions for in tera ting go o ds. A ore omp onen t of our approa h learns a mo del of the empiri al pri e dynami s based on past data and uses the mo del to analyti ally al ulate, to the greatest exten t p ossible, optimal bids. W e in tro du e a new and general b o osting-based algorithm for onditional densit y estimation problems of this kind, i.e., sup ervised learning problems in whi h the goal is to estimate the en tire onditional distribution of the real-v alued lab el. This approa h is fully implemen ted as A TT a -2001, a tops oring agen t in the se ond T rading Agen t Comp etition (T A C-01). In an au tion for a single go o d, it is straigh tforw ...