We consider the problem faced by a firm that receives highly differentiated products in an online fashion. The firm needs to price these products to sell them to its customer base. Products are des...

Feature-Based Dynamic Pricing

We consider the problem faced by a firm that receives highly differentiated products in an online fashion and needs to set prices so as to sell them to its customer base. Products are described by vectors of features and the market value of each product is assumed to be linear in the values of the features. The firm does not initially know the values of the different features, but it can learn the values of the features based on whether products sold at the posted prices in the past. This model is motivated by a question in online advertising where impressions arrive over time and can be described by vectors of features. We first consider a multi-dimensional version of binary search over polyhedral sets, and show that it has exponential worst-case regret in the dimension of the feature space. We then show that a modification of the prior algorithm, where uncertainty sets are replaced by their Lowner-John ellipsoids has a worst-case regret that is quadratic in the dimension of the feature space and logarithmic in the time horizon.

https://papers.ssrn.com/sol3/Delivery.cfm/SSRN_ID2883579_code1626962.pdf?abstractid=2737045&mirid=1

The application to search ranking is one of the biggest machine learning success stories at Airbnb. Much of the initial gains were driven by a gradient boosted decision tree model. The gains, however, plateaued over time. This paper discusses the work done in applying neural networks in an attempt to break out of that plateau. We present our perspective not with the intention of pushing the frontier of new modeling techniques. Instead, ours is a story of the elements we found useful in applying neural networks to a real life product. Deep learning was steep learning for us. To other teams embarking on similar journeys, we hope an account of our struggles and triumphs will provide some useful pointers. Bon voyage!

Applying Deep Learning to Airbnb Search

Price discrimination strategies, which offer different prices to customers based on differences in their valuations, have become common practice. While it allows sellers to increase their profits, it also raises several concerns in terms of fairness, e.g., by charging higher prices (or denying access) to protected minorities in case they have higher (or lower) valuations than the general population. This topic has received extensive attention from media, industry, and regulatory agencies. In this paper, we consider the problem of setting prices for different groups under fairness constraints. We first propose four definitions: fairness in price, demand, consumer surplus, and no-purchase valuation. We prove that satisfying more than one of these fairness constraints is impossible even under simple settings. We then analyze the pricing strategy of a profitmaximizing seller and the impact of imposing fairness on the seller’s profit, consumer surplus, and social welfare. Under a linear demand model, we find that imposing a small amount of price fairness increases social welfare, whereas too much price fairness may result in a lower welfare relative to imposing no fairness. On the other hand, imposing fairness in demand or consumer surplus always decreases social welfare. Finally, no-purchase valuation fairness always increases social welfare. We observe similar patterns under several extensions and for other common demand models numerically. Our results and insights provide a first step in understanding the impact of imposing fairness in the context of discriminatory pricing.

Price Discrimination with Fairness Constraints

Applying Deep Learning To Airbnb Search

This paper describes the pricing strategy model deployed at Airbnb, an online marketplace for sharing home and experience. The goal of price optimization is to help hosts who share their homes on Airbnb set the optimal price for their listings. In contrast to conventional pricing problems, where pricing strategies are applied to a large quantity of identical products, there are no "identical" products on Airbnb, because each listing on our platform offers unique values and experiences to our guests. The unique nature of Airbnb listings makes it very difficult to estimate an accurate demand curve that's required to apply conventional revenue maximization pricing strategies. Our pricing system consists of three components. First, a binary classification model predicts the booking probability of each listing-night. Second, a regression model predicts the optimal price for each listing-night, in which a customized loss function is used to guide the learning. Finally, we apply additional personalization logic on top of the output from the second model to generate the final price suggestions. In this paper, we focus on describing the regression model in the second stage of our pricing system. We also describe a novel set of metrics for offline evaluation. The proposed pricing strategy has been deployed in production to power the Price Tips and Smart Pricing tool on Airbnb. Online A/B testing results demonstrate the effectiveness of the proposed strategy model.

Customized Regression Model for Airbnb Dynamic Pricing

Existing theories of media competition imply that advertisers will pay a lower price in equilibrium to reach consumers who multi-home across competing outlets. We generalize and extend this theoretical result and test it using data from television and social media advertising. We find that television outlets whose viewers watch more television charge a lower price per impression to advertisers. This finding helps rationalize well-known stylized facts such as a premium for younger and more male audiences on television. Also consistent with the theory, we show that social media advertising markets feature a premium for older audiences. A quantitative version of our model whose only free parameter is a scale normalization can explain 35 percent of the variation in price per impression across owners of television networks, and aligns with recent trends in television advertising revenue. We use the model to quantify the impact of mergers, the effect of competition on incentives to produce content, and the effect of Netflix ad carriage on prices for linear television advertising. JEL codes: L10, L82, M37

/pdf/pricing-power-in-advertising-markets-theory-and-evidence-c0oc5t4w.pdf

Frank Yang

Papers

Customized Regression Model for Airbnb Dynamic Pricing

Pricing Power in Advertising Markets: Theory and Evidence

Multi-lane’s control performance differentiation on traffic efficiency under the lane-level dynamic coordination strategy