Dynamic Pricing for Airline Ancillaries with Customer Context

Abstract

Ancillaries have become a major source of revenue and profitability in the travel industry. Yet, conventional pricing strategies are based on business rules that are poorly optimized and do not respond to changing market conditions. This paper describes the dynamic pricing model developed by Deepair solutions, an AI technology provider for travel suppliers.We present a pricing model that provides dynamic pricing recommendations specific to each customer interaction and optimizes expected revenue per customer. The unique nature of personalized pricing provides the opportunity to search over the market space to find the optimal price-point of each ancillary for each customer, without violating customer privacy.In this paper, we present and compare three approaches for dynamic pricing of ancillaries, with increasing levels of sophistication:(1) a two-stage forecasting and optimization model using a logistic mapping function; (2) a two-stage model that uses a deep neural network for forecasting, coupled with a revenue maximization technique using discrete exhaustive search; (3) a single-stage end-to-end deep neural network that recommends the optimal price. We describe the performance of these models based on both offline and online evaluations. We also measure the real-world business impact of these approaches by deploying them in an A/B test on an airline's internet booking website. We show that traditional machine learning techniques outperform human rule-based approaches in an online setting by improving conversion by 36% and revenue per offer by 10%. We also provide results for our offline experiments which show that deep learning algorithms outperform traditional machine learning techniques for this problem. Our end-to-end deep learning model is currently being deployed by the airline in their booking system.

Negotiating Networks in Oligopoly Markets for Price-Sensitive Products

“…This function is inspired from strategic model proposed by Ye et al [12] and -insensitive loss used in SVR [31]. The enhanced version of this function heuristically incorporates the monotonicity in the willingness to pay as mentioned in Shukla et al [13]. The boundary function penalizes the networks for violating upper and lower bounds as follows:…”

“…Customer characteristics and the seller's ability to price discriminate are also shown to significantly influence overall revenue and profit [11]. It has been demonstrated that dynamic pricing using buyers' context can achieve higher conversion rates as well as revenue per offer by the sellers [12,13]. As far as buyer behaviour modeling is concerned, multiple theoretical models [14,15,16] based on risk perception, knowledge levels and bounded rationality; and discrete choice models [17] are typically used.…”

Distribution Shift in Airline Customer Behavior during COVID-19

“…Shukla et al [12] proposed a two-stage pricing model that uses the purchase probability prediction for price recommendation. Figure 5 shows the proposed pricing framework with shift detection before the supervised model prediction.…”

“…Machine learning applications often implicitly or explicitly assume that data sets are drawn from stationary distributions, and the sudden shift in underlying data makes the model prone to break. Pricing based on context is one such application that is prominently driven by customers' behaviour [14,12]. The motivation of this work stems from examining the performance of machine learning models deployed to price add-on (ancillary) products for an international airline.…”

Protecting Consumers Against Personalized Pricing: A Stopping Time Approach

“…Regardless of the societal or ethical implications, personalized pricing schemes are currently deployed in practice. Airlines use them to price ancillary services and products, such as in-flight meals, baggage allowance, and legroom [28]. On websites such as Orbitz, Expedia, Hotels.com, and Priceline, the offered options and pricing of plan tickets, hotels, and car rentals depend on the consumer's features (e.g.…”