Pricing

The definitive textbook on revenue management covering pricing, capacity control, and overbooking.

Framework for dynamic pricing with finite inventory and strategic consumers.

Comprehensive practitioner's guide to pricing strategy and optimization techniques.

The foundational paper for dynamic pricing theory—establishes intensity control formulation, proves optimality of monotonically decreasing prices. 4,000+ citations.

Extends dynamic pricing to multiple products sharing capacity constraints—the theoretical foundation for airline network revenue management and cloud computing.

Multi-location markdown optimization balancing store-level heterogeneity.

Bayesian approach to learning demand while optimizing markdown paths.

The definitive paper on fast fashion economics—models how Zara-style systems mitigate strategic consumer behavior and reduce markdowns.

Foundational paper on multi-store clearance optimization using stochastic dynamic programming with real Falabella case study.

The definitive survey on explore-exploit pricing literature—synthesizes OR/MS, economics, marketing, and CS covering regret bounds and bandit connections.

Joint optimization of pricing and matching in two-sided rideshare markets.

Empirical analysis of Uber's surge pricing showing welfare improvements from reduced search frictions.

Estimates labor supply elasticity and value of flexibility using Uber driver data.

The workhorse model for dynamic congestion pricing theory—operationalized Vickrey's bottleneck concept with endogenous departure decisions and time-varying tolls.

The foundational paper on two-sided market pricing—derives optimal price allocation explaining why platforms price asymmetrically across sides.

Introduces the competitive bottlenecks framework where one side multi-homes—explains monopoly power over access to single-homing customers.

Analyzes welfare effects of machine learning-based personalized pricing.

How algorithmic pricing affects competition and market outcomes.

The seminal paper on behavior-based price discrimination—foundational duopoly model showing how firms use purchase history to discriminate. 2,000+ citations.

The definitive JEL survey on privacy and personal data economics—covers consumer tracking, welfare implications, and regulatory frameworks.

Key paper demonstrating ML enables first-degree price discrimination—shows big data increases potential profits by 14.55% vs 0.14% from demographics alone.

The foundational random coefficients discrete choice model for demand estimation.

Practical guide to implementing BLP-style demand models with market-level data.

Modern implementation and extensions of BLP with diagnostics and best practices.

The foundational paper introducing the critical inversion technique for demand estimation—enables estimation with IVs despite endogenous prices.

Pioneered combining micro-level consumer data with aggregate market shares—foundation for modern 'micro moments' approaches in pyBLP.

The workhorse paper for online price experimentation—extends MAB algorithms to incorporate microeconomic choice theory. 43% profit improvements.

Field-defining paper establishing theoretical framework for dynamic pricing with demand learning. Pioneered regret-based analysis with √T regret bounds.

Introduces elegant Controlled Variance Pricing (CVP) policy with 'taboo interval' for exploration. Achieves logarithmic regret while being highly implementable.

Bridges bandit algorithms and practical pricing by applying Thompson sampling to network revenue management with inventory constraints. Validated at Rue La La.

Models settings where sellers can make at most m price changes. Characterizes optimal regret as O(log^m T). Includes real implementation at Groupon.

Pioneering work on contextual pricing where products have feature vectors. Uses ellipsoid method to achieve O(d² log d) regret. Winner of 2024 Revenue Management Prize.

Foundational paper on two-part tariffs. Should Disneyland charge high admission with free rides, or free entry with high per-ride prices? 600+ citations.

Extends nonlinear pricing theory to multidimensional screening with multiple products. Foundational for product line design.

Landmark paper showing that sufficiently intense competition eliminates quality distortions, yielding efficient 'cost-plus-fee' pricing.

Field-defining paper on behavioral pricing and three-part tariffs. Shows consumer overconfidence explains cell phone plan structures. Uses real cellular billing data.

Rigorous foundations for freemium models (Spotify, YouTube). Shows optimal menu consists of exactly two services—ad-supported free and ad-free premium.

Field-defining paper showing Q-learning algorithms autonomously learn supracompetitive prices without communication, sustaining collusion through punishment strategies.

Extends Calvano et al. to sequential (Stackelberg) pricing environments, showing Q-learning converges to collusive equilibria even with turn-taking.

Shows pricing algorithms generate supracompetitive prices through competitive equilibrium—no collusion required. Uses high-frequency empirical data from online retailers.

Definitive JEL survey on privacy economics—essential for understanding personalized pricing and price discrimination enabled by algorithmic data collection.

Leading competition law analysis explaining the legal gap: tacit collusion is harmful but lawful under current antitrust frameworks.

Definitive reference on Thompson sampling covering Bernoulli bandits, product recommendation, assortment optimization, and RL in MDPs.

First theoretical regret guarantees for contextual Thompson Sampling. Proves Õ(d√T) regret bounds. Novel martingale-based analysis became the template for subsequent work.

Shows Θ(√T) regret for general parametric demand with MLE estimation. Important bridge between econometric demand estimation and online learning theory.

Landmark industry application from Amadeus. Demonstrates deep RL for airline pricing that learns directly from customer interactions without demand forecasting.