pricing

This study investigates how online platforms jointly leverage three strategic instruments—pricing (commissions and transaction prices), matching (recommendation and search mechanisms), and bundling (product assortment)—to simultaneously enhance platform revenue and improve overall market welfare. By developing a game-theoretic model of multi-sided interactions and integrating equilibrium analysis with mechanism design theory, the paper systematically uncovers the mechanisms through which the interplay of these levers shapes participant behavior, transaction structures, and value distribution. The findings elucidate the intrinsic coupling among key platform design dimensions and offer theoretical foundations for governance strategies that balance efficiency and fairness in digital markets.

This paper addresses the dynamic pricing problem in appointment-based services featuring multi-tiered, multi-temporal, and multi-window substitutable options (e.g., varying time slots, prices, and capacity levels). We propose a unified framework integrating hierarchical discrete choice modeling with dynamic pricing. Our approach innovatively employs decision trees to drive interpretable market segmentation and segment-specific parametric choice models—explicitly incorporating reference price effects. We further design an efficient heuristic algorithm for scalable pricing optimization. An A/B test conducted on an Amazon business line demonstrated a 19% improvement in core metrics; the solution was fully deployed starting Q4 2023, enabling rapid iteration of new services. To our knowledge, this is the first work to jointly integrate interpretable segmentation, behavior-aware choice modeling, and scalable pricing optimization—significantly enhancing demand forecasting accuracy and revenue performance in complex appointment settings.

SaaS pricing models have grown increasingly complex—featuring dozens to thousands of configurable parameters—rendering manual management error-prone and unsustainable. To address this, we propose a pricing-driven DevOps automation framework. Our method systematically defines seven core pricing analysis operations and innovatively formalizes semantic pricing as a Constraint Satisfaction Optimization Problem (CSOP), enabling automatic translation from natural-language specifications or business rules into executable logical constraints. Leveraging MiniZinc, we implement iPricing: a verifiable, optimization-ready, machine-readable pricing model. Evaluated on over 150 real-world SaaS pricing configurations, our framework successfully identified 35 logical defects—including inconsistencies, redundancies, and coverage gaps—demonstrating substantial improvements in configuration reliability and DevOps automation maturity.

This paper addresses dynamic pricing under completely unknown demand functions, aiming to eliminate restrictive parametric assumptions and enhance practical applicability. We propose a nonparametric Bayesian optimization framework based on Gaussian processes (GPs), unifying treatment of both infinite- and finite-horizon inventory settings. The method performs sequential price decisions to balance exploration and exploitation, and—crucially—provides the first theoretical regret bound for this nonparametric setting. Demand uncertainty is modeled via a GP prior, and adaptive price updates are guided by an acquisition function, requiring no assumption on the functional form of demand. Experiments demonstrate that our approach significantly outperforms state-of-the-art reinforcement learning algorithms in cumulative revenue, robustness to demand misspecification, and sample efficiency, validating its effectiveness and practicality in highly uncertain environments.

This study addresses the challenges of extreme demand volatility, delayed pricing responses, and misalignment between short-term revenue and long-term profitability during major fashion e-commerce promotions. To tackle these issues, the authors propose a high-frequency “predict–optimize” automated pricing system that breaks away from traditional weekly decision cycles by operating at a minute-level granularity. The system achieves the first industrial-scale deployment of daily multi-objective dynamic pricing in large-scale e-commerce settings, combining gradient-boosted tree models for daily demand forecasting with a multi-objective optimization framework to generate real-time pricing strategies that jointly maximize long-term profit and net merchandise value. Evaluated across 23 A/B tests in 12 Zalando markets from 2023 to 2024, the system delivered approximately 6% higher profit while maintaining sales volume and has since been fully deployed for promotional pricing.

This study addresses the design of optimal pricing mechanisms for sequential information seekers: a buyer inspects stochastic options one by one following the Pandora’s rule, while a seller commits to non-adaptive prices for value revelations to maximize expected revenue. The authors propose a concise pricing scheme based on equalizing Weitzman indices, achieving a 4-approximation to the optimal revenue under general distributions. They fully characterize the optimal pricing structure in special cases such as identical distributions or monotone hazard rates, and establish tight approximation guarantees in a variant allowing optional inspection. The analysis integrates tools from mechanism design, the Pandora’s box model, and approximation algorithm theory.

This paper addresses the suboptimal revenue performance in dynamic pricing of complementary products arising from neglecting demand interdependencies. To tackle this, we propose a synergistic pricing framework that jointly models demand structure and enables online learning. Methodologically, we develop a heteroscedastic Gaussian process model incorporating both positive and negative demand interactions, integrate it with a multi-armed bandit for sequential decision-making, and employ integer programming to automatically discover complementarity relationships. Unlike conventional single-product optimization paradigms, our approach enables end-to-end learning of joint pricing policies. In simulation experiments, our method significantly outperforms baseline algorithms that ignore demand interactions, demonstrating the critical role of explicit complementarity modeling in enhancing dynamic pricing efficacy. The framework offers a novel, interpretable, and scalable paradigm for data-driven retail pricing.

This work proposes a dynamic pricing framework that operates without assuming a parametric form of the demand function, under the challenging setting where only single-point revenue observations are available and market conditions evolve non-stationarily. The approach constructs a nonparametric gradient estimator from single-point revenue feedback to iteratively update prices and incorporates a restart mechanism to handle abrupt environmental shifts. When the degree of non-stationarity is unknown, a meta-learning layer is introduced to adaptively combine multiple restart strategies. Theoretical analysis establishes an upper bound on the cumulative revenue regret, and extensive experiments on both synthetic and real-world data demonstrate the method’s effectiveness and robustness in non-stationary markets. This study represents the first integration of nonparametric learning, single-point feedback-based gradient estimation, and adaptive restarting, achieving provably sound performance guarantees.

We study competitive dynamic pricing among multiple sellers, motivated by the rise of large-scale experimentation and algorithmic pricing in retail and online marketplaces. Sellers repeatedly set prices using simple learning rules and observe only their own prices and realized demand, even though demand depends on all sellers'prices and is subject to random shocks. Each seller runs two-point A/B price experiments, in the spirit of switchback-style designs, and updates a baseline price using a linear demand estimate fitted to its own data. Under certain conditions on demand, the resulting dynamics converge to a Conjectural Variations (CV) equilibrium, a classic static equilibrium notion in which each seller best responds under a conjecture that rivals'prices respond systematically to changes in its own price. Unlike standard CV models that treat conjectures as behavioral primitives, we show that these conjectures arise endogenously from the bias in demand learning induced by correlated experimentation (e.g., due to synchronized repricing schedules). This learning bias selects the long-run equilibrium, often leading to supra-competitive prices. Notably, we show that under independent experimentation, this bias vanishes and the learning dynamics converge to the standard Nash equilibrium. We provide simple sufficient conditions on demand for convergence in standard models and establish a finite-sample guarantee: up to logarithmic factors, the squared price error decays on the order of $T^{-1/2}$. Our results imply that in competitive markets, experimentation design can serve as a market design lever, selecting the equilibrium reached by practical learning algorithms.

This study addresses the design of optimal pricing mechanisms for data markets under budget-constrained rational buyers. Focusing on scenarios where buyers aim to maximize predictive accuracy by selecting data bundles within a fixed budget, the work proposes a class of monotone continuous pricing functions to maximize total market revenue. Theoretical analysis reveals that the optimal pricing function exhibits a piecewise-linear convex structure, with the number of breakpoints bounded by the number of buyers. While general nonlinear pricing can be solved in polynomial time, linear pricing—despite its apparent simplicity—is shown to be APX-hard, highlighting a striking computational dichotomy. To address this challenge, the paper develops an online 2-approximation algorithm and an offline $(1-1/e)^{-1}$-approximation algorithm, providing foundational insights for pricing theory in data markets.