In online advertising markets, setting budget and return on investment (ROI) constraints are two prevalent ways to help advertisers (i.e. buyers) utilizelimited monetary resources efficiently . In this work, we provide a holistic view of ROI and budget constrained markets . We show that the optimal buyer hindsight policy admits a”threshold-based” structure that suggests the buyer win all auctions duringwhich her valuation-to-expenditure ratio is greater than some threshold . We further propose a threshold-based bidding framework that aims to mimic thehindsight bidding policy by learning its threshold . When facingstochastic competition, our algorithm guarantees the satisfaction of both budget and ROI constraints and achieves sublinear regret compared to theoptimal hindsight policy . We also propose a pricingalgorithm that utilizes an episodic binary-search procedure to identify arevenue-optimal selling price. During each binary search episode, our pricingalgorithms explore a particular price, allowing the buyer’s learning algorithm

Author(s) : Negin Golrezaei, Patrick Jaillet, Jason Cheuk Nam Liang, Vahab Mirrokni

Links : PDF - Abstract

Code :
Coursera

Keywords : budget - threshold - roi - bidding - policy -

Leave a Reply

Your email address will not be published. Required fields are marked *