Learning Optimal Personalised Reservation Prices in Impression Ad Auctions with Mixture Density Networks

Reservation prices have proven effective in boosting revenue in Generalised Second Price (GSP) auctions, particularly in cost-per-click (CPC) settings. However, in domains like music streaming, where ads are consumed passively without user clicks, a cost-per-impression (CPM) model is more appropriate. Additionally, in the music streaming domain, user intent is typically unknown, unlike in sponsored search, making it essential to optimally leverage all available user and contextual information when setting prices. This paper addresses the challenge of optimising reservation prices in GSP auctions with CPM pricing, adopting a personalised approach that accounts for both user- and advertiser-specific factors. Using dataset of 100,000 auctions from a major music streaming service, we determine such optimal prices. To achieve this, we first derive the symmetric Nash equilibrium for GSP auctions in a CPM context. We then introduce a Deep Neural Network-based mixture density model that incorporates this equilibrium into its loss. This model captures advertisers' diverse preferences by learning directly from bidding data. We show how this approach enables the computation of personalised prices for both users and advertisers, boosting auction revenue by an average of +4% across ten markets. Our study further highlights the impact of market competitiveness and advertiser preference heterogeneity on revenue gains, showing that personalised pricing greatly enhances auction performance.

• Publication year

  2025

• Venue

  International Conference on Information and Knowledge Management

• Publication date

  2025-11-10

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3746252.3761070
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Off-Policy Learning-to-Bid with AuctionGym

  2023cited by this paper
• Microeconomic Theory

  2022cited by this paper
• Personalized Pricing and Consumer Welfare

  2022cited by this paper
• Linear Program-Based Approximation for Personalized Reserve Prices

  2021cited by this paper
• On structural and practical identifiability

  2021cited by this paper
• Dynamic Pricing under Competition on Online Marketplaces: A Data-Driven Approach

  2018cited by this paper
• Customized Regression Model for Airbnb Dynamic Pricing

  2018cited by this paper
• Reinforcement Mechanism Design, with Applications to Dynamic Pricing in Sponsored Search Auctions

  2017cited by this paper
• Reinforcement mechanism design

  2017cited by this paper
• Machine Learning Methods for Demand Estimation

  2015cited by this paper
• Reserve Prices in Internet Advertising Auctions: A Field Experiment

  2011cited by this paper
• Revenue maximization with a single sample

  2010cited by this paper
• Bayes-nash equilibria of the generalized second price auction

  2009cited by this paper
• Structural and practical identifiability analysis of partially observed dynamical models by exploiting the profile likelihood

  2009cited by this paper
• Strategic bidder behavior in sponsored search auctions

  2007cited by this paper
• Revenue analysis of a family of ranking rules for keyword auctions

  2007cited by this paper
• Mixture Density Networks

  1994cited by this paper
• Optimal Auction Design

  1981cited by this paper
• Multipart pricing of public goods

  1971cited by this paper
• Counterspeculation, Auctions, And Competitive Sealed Tenders

  1961cited by this paper

• No citing papers are available for this paper.