Optimizes Airbnb pricing to increase revenue and reduce booking regret.
problem Maximizing revenue in an online marketplace with competing products.
method Two-stage model to price retrieved items based on learned distributions of their values.
result Improves revenue and booking regret by at least +20% and +55% respectively.
Algorithm COOL coordinates online learners to improve user preference learning.
problem Learning user preferences in a multi-task setting with sequential data.
method COOL algorithm coordinates task-specific online learners via weighted projections onto a convex set.
result COOL algorithm achieves better user preference learning with reduced computation/communication costs.
A commonly expressed concern about the rise of the peer-to-peer rental market Airbnb is that hosts---those renting out their properties---impose costs on their unwitting neighbors. I consider the question of whether apartment building owners will, in a competitive rental market, set a building-specific Airbnb hosting p…
Predicts Airbnb listing prices based on attributes for host profitability.
problem Optimizing Airbnb listing prices for host profitability and guest affordability.
method Data exploration, transformations, machine learning models, experiments.
result Developed a model for optimal Airbnb listing prices.
Paper tackles diversity in Airbnb search results.
problem Show diverse results to improve user experience.
method Heuristic based approaches → Deep learning solution using RNNs.
result Novel deep learning solution improves diversity in search results.
This paper explores using neural networks to improve Airbnb search performance.
problem Plateaued gains from gradient boosted decision tree model in search ranking.
method Applied neural networks to improve search performance.
result Shows elements useful in applying neural networks to a real-life product.
Paper predicts Airbnb prices using machine learning and customer reviews.
problem Predicting optimal Airbnb prices with limited property information.
method Uses machine learning, sentiment analysis, and various models.
result Develops a model to help both property owners and customers with price evaluation.
Study analyzes Airbnb booking lead times during global crises using a new metric.
problem Disruptions in booking behaviors during global crises affect forecasting accuracy.
method Normalized L1 (Manhattan) distance to assess lead time divergences.
result Identified two-phase disruption: abrupt change at pandemic onset followed by partial recovery.
Improves deep learning for Airbnb search ranking.
problem Challenges in ranking inventory and handling new listings.
method New ranking neural network architecture, positional bias handling, and cold start solutions.
result Significant improvements in inventory ranking and new listing treatment.
Study analyzes Airbnb lead-time distributions for Nights Booked and Gross Booking Value, finding divergent shapes and tail behavior.
problem Analyzing lead-time distributions for Airbnb demand metrics.
method Compositional analysis of daily lead-time vectors, fitting Gamma, Weibull, and Lognormal distributions, using generalized Pareto for tail inference.
result Lead-time distributions for Nights Booked and Gross Booking Value diverge, with GBV concentrating more in mid-range horizons.
Deep neural networks improve recommendation accuracy in marketplaces.
problem Measuring and optimizing recommender performance in marketplaces.
method Hybrid item representation models, sequence-based models, and multi-armed bandit models.
result Promising deep neural network recommenders are currently in production at FINN.no.
Deep learning improves recommendation systems for marketplaces.
problem Challenges in matrix factorization for marketplaces.
method Hybrid recommender system combining user-generated contents and user behavior data.
result Five lessons learned from deep learning experiments.
A new pricing strategy maximizes revenue in high-dimensional product spaces with varying customer preferences.
problem Maximizing revenue in a high-dimensional product space with heterogeneous price sensitivity.
method Proposes M3P, a pricing policy that achieves a specific regret bound under heterogeneous price sensitivity.
result Achieves a T T T -period regret of O ( log ( T d ) ( T + d log ( T ) ) ) O(\log(Td) (\sqrt{T} + d\log(T))) O ( log ( T d ) ( T + d log ( T ))) . Study incentivizes sharing economy users to explore less-reviewed options.
problem Lack of reviews leads to neglect of less-popular options, creating a cycle.
method Introduced Coordinated Online Learning (CoOL) to learn optimal incentives.
result Algorithm increases exploration on Airbnb, improving user experience.
Paper proposes machine learning for pricing 3D printing services in marketplaces.
problem Inefficient pricing methods for 3D printing services in marketplaces.
method Data mining and machine learning methods to estimate price ranges based on supplier and customer characteristics.
result Machine learning model achieves 65% accuracy for US suppliers and 59% for Europe suppliers in classifying 3D printer listings.
MARS-Gym framework for marketplaces to train and evaluate recommender systems.
problem Challenges in designing, training, and evaluating recommender systems in marketplaces.
method Open-source framework for Reinforcement Learning agents in marketplaces.
result Empowers researchers and engineers to quickly build and evaluate agents for recommendations.
A scalable system detects price anomalies in online marketplaces to improve customer experience.
problem Inaccurate prices on online marketplaces lead to poor customer experience and revenue loss.
method MoatPlus uses unsupervised statistical features and an ensemble of models to generate upper price bounds.
result Our approach improves precise anchor coverage by up to 46.6% in high-vulnerability item subsets.
Proposes a framework for fairness in two-sided marketplaces.
problem Achieving fairness in two-sided marketplaces.
method Developed an end-to-end framework for fairness constraints from both sides of the marketplace, including dynamic aspects.
result Efficacy of the proposed framework demonstrated through simulations.
Optimizes bidding strategies for LinkedIn ads across multiple platforms.
problem Optimizing automated bidding agents for dynamic online marketplaces.
method Developed a general optimization framework for buyer's interest, agnostic to auction mechanisms.
result Automatically guarantees the optimality of budget allocation across ad units and platforms.
Genie optimizes search marketplaces by estimating policy impacts without risky experiments.
problem Optimizing search marketplaces with frequent policy changes and limited randomized experiments.
method Genie uses an open box simulation engine and click calibration model to estimate KPI impacts.
result Genie outperforms existing approaches in optimizing Bing Ads Marketplace.
Uber optimizes marketplace levers using machine learning to improve resource allocation efficiency.
problem Optimizing budget allocation for drivers and riders to maximize business value.
method End-to-end machine learning and optimization procedure using feature store, model training, and ADMM.
result Substantially improved Uber's resource allocation efficiency through high-dimensional optimization.
Study fair team formation in online labor marketplaces.
problem Design fair algorithms for team formation in online labor marketplaces.
method Define and analyze the Fair Team Formation problem, provide inapproximability results, and develop four algorithms.
result Developed four algorithms for fair team formation in online labor marketplaces.
Bayesian deep learning improves predictive performance in high-dimensional data.
problem Improving predictive performance in high-dimensional data.
method A Bayesian perspective on deep learning, including stochastic gradient descent and dropout.
result Deep learning provides predictive performance gains over shallow learners.
GCF estimates heterogeneous treatment effects for continuous treatments in online marketplaces.
problem Estimating heterogeneous treatment effects for continuous treatments in online marketplaces.
method Kernel-based doubly robust estimator and distance-based splitting criterion.
result GCF estimates heterogeneous treatment effects for continuous treatments effectively.
Framework for optimizing search engine rankings using observational data.
problem Optimizing ranking policies for search engines using limited observational data.
method Formulated expected reward optimization problem, estimated context value distribution, trained ranking policy via Bayesian inference.
result Demonstrated trade-offs in ranking policies trained on empirical reward estimates.
This paper optimizes search experiences in two-sided marketplaces by balancing multiple conflicting metrics.
problem Balancing conflicting business metrics in two-sided marketplaces like eBay and Etsy.
method Joint optimization of market-level metrics using Evolutionary Strategies.
result Demonstrated effectiveness of the proposed method on Etsy data.
NFTs revolutionize art sales by providing proof of ownership.
problem Lack of provenance and authenticity in digital art.
method Analysis of major art NFT marketplaces.
result NFTs reduce the need for intermediaries in the art trade.
A new mechanism optimizes data marketplace pricing efficiently.
problem Designing fair and efficient pricing mechanisms for data marketplaces.
method Two-stage approach: auctions to estimate value distributions, then optimal posted prices.
result MAPP achieves optimal revenue with minimal price discrimination.
Study fairness in intervention to maximize outcomes.
problem Fairness in intervention on a given node.
method Counterfactual estimation with partial causal model knowledge.
result Theoretical guarantees on error probability and effectiveness of algorithm.
Research shows a significant increase in stay lengths for digital nomads in the U.S. during and after the pandemic.
problem Shifts in stay lengths for digital nomads during and after the pandemic.
method Analysis of Airbnb reservations data from 2019-2024, using statistical models to quantify changes.
result Mean stay lengths increased from 3.68 to 4.36 nights, stabilizing near 4.07 after 2021, indicating a 10% increase from pre-pandemic levels.
Bayesian model predicts evolving guest origin markets in tourism.
problem Forecasting the changing composition of guest origin markets in tourism.
method Developed and applied Bayesian Dirichlet autoregressive moving average (BDARMA) models to Airbnb booking data.
result BDARMA models achieve lower forecast error and competitive performance in guest origin market shares.
Bayesian models predict evolving guest origin markets in tourism.
problem Forecasting the changing composition of guest origin markets in tourism.
method Developed and applied Bayesian Dirichlet autoregressive moving average (BDARMA) models to Airbnb booking data.
result BDARMA models outperform standard benchmarks in forecasting guest origin market shares.
Suppliers (including companies and individual prosumers) may wish to protect their private information when selling items they have in stock. A market is envisaged where private information can be protected through the use of differential privacy and option contracts, while privacy-aware suppliers deliver their stock a…
A new dataset tracks user interactions and click responses in online marketplaces.
problem Lack of exposure data in recommender systems datasets.
method Proposes a novel dataset including slates and click responses, allowing more accurate likelihood models.
result Models using exposure data show more natural likelihood, reducing bias towards previously exposed items.
New estimator reduces bias in interference studies on content marketplaces.
problem Interference bias in experiments on content marketplaces like Douyin.
method Developed a Monte-Carlo estimator based on DQ techniques.
result Achieved bias second-order in treatment effect with low variance.
Market incentivizes parties to share high-quality data for collaborative machine learning tasks.
problem Fair revenue distribution and data replication threats in collaborative machine learning markets.
method Introduces a novel payment division function robust to replication and customized output models.
result Validated assumptions and showed approximate satisfaction for commonly used models.
Sample-Rank simplifies MO recommendations by sampling and ranking, improving revenue with stable conversion rates.
problem Multi-objective recommendations in online food ordering systems.
method Multi-goal sampling followed by ranking, reducing MO problem to LTR model.
result Significant lift in revenue (2.64%) with stable conversion rates, no drop in last-mile traversal.
Alternative app data improves credit scoring for underserved borrowers.
problem Improving credit scoring for low-wealth and young individuals.
method Use of alternative data from app-based marketplaces, validated with TreeSHAP method.
result Alternative data sources predict financial behavior better than traditional bureau data.
Efficiently projects points onto polytopes, especially useful in web-scale applications.
problem Efficiently projecting points onto polytopes in large-scale applications.
method Developed a vertex-oriented incremental algorithm for polytope projection, tailored for simplex and unit-box cut polytopes.
result Majority of projections lie on vertices of polytopes, leading to significant performance improvements.
Improved model accuracy can reduce overall user accuracy in competitive markets.
problem The impact of model competition on overall user accuracy.
method Defined a model of competition for classification tasks and used data representations to study the effect of scale.
result Improving data representation quality can decrease overall predictive accuracy across users (social welfare) in a competitive market.
Paper proposes MBP framework to price ML model instances directly, not data.
problem Reducing data acquisition cost without losing revenue or efficiency.
method Formal properties, noise injection approach, algorithmic solutions.
result MBP framework maximizes seller revenue and buyer affordability.
In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers. Workers will be paid for each label they provide, but the labeling requester usually has only a limited amount of the budget. Since data instances have different levels of labeling difficulty and workers have different r…
Tangled String visualizes stock market changes at various timescales.
problem Explaining multi-scale contextual shifts in stock market prices.
method Sequence visualization tool based on metaphor of tangled strings.
result Change points in stock prices coincide with real changes.
The paper addresses Qini curve estimation under clustered network interference.
problem Qini curves can be biased when interference is ignored in clustered network settings.
method Proposes three estimation strategies for clustered network interference.
result Identifies the most appropriate approach based on bias-variance trade-offs.
Firm optimizes pricing for many products with varying features and customer choices.
problem Optimizing pricing for a large number of products with varying features and customer choices.
method Proposes a dynamic pricing policy, Regularized Maximum Likelihood Pricing (RMLP), leveraging the sparsity of the high-dimensional model.
result Achieves logarithmic regret in T T T for minimizing revenue loss against a clairvoyant policy. Study breaks down graphs into structural and featural components for task-agnostic data valuation.
problem Lack of methods to assess the value of graphs in data marketplaces.
method Introduces blind message passing framework to evaluate graphs without specific task metrics.
result Demonstrates effectiveness in capturing structural disparities, relevance, and diversity of seller data for buyers.
The paper introduces Absolute Shapley Value to handle negative contributions in machine learning model training.
problem Negative marginal contributions in machine learning model training.
method Investigates three philosophies: Original Shapley Value, Zero Shapley Value, and Absolute Shapley Value.
result Absolute Shapley Value significantly outperforms other definitions in evaluating data importance.
A new sampler tackles high-dimensional models with intractable likelihoods.
problem Statistical inference for models with computationally intractable likelihoods and high-dimensional parameters.
method Likelihood-free approximate Gibbs sampler focusing on lower-dimensional conditional distributions estimated by flexible regression models.
result The sampler enables fitting models with 13,140 parameters that are otherwise impossible with standard ABC techniques.