Dynamic Pricing for Airline Ancillaries with Customer Context

Naman Shukla, Arinbjörn Kolbeinsson, Ken Otwell, Lavanya Marla, Kartik Yellepeddi

Research output: Contribution to conferencePaper

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.
Original languageEnglish (US)
Pages2174-2182
DOIs
StatePublished - 2019
Eventthe 25th ACM SIGKDD International Conference - Anchorage, AK, USA
Duration: Aug 4 2019Aug 8 2019

Conference

Conferencethe 25th ACM SIGKDD International Conference
Period8/4/198/8/19

Fingerprint

Airlines
Dynamic pricing
Revenue
Deep learning
Neural networks
Machine learning
Experiment
Logistics
Interaction
Rule-based
Optimization model
Suppliers
Two-stage model
Evaluation
Pricing
World Wide Web
Profitability
Web sites
Travel industry
Revenue maximization

Cite this

Shukla, N., Kolbeinsson, A., Otwell, K., Marla, L., & Yellepeddi, K. (2019). Dynamic Pricing for Airline Ancillaries with Customer Context. 2174-2182. Paper presented at the 25th ACM SIGKDD International Conference, . https://doi.org/10.1145/3292500.3330746

Dynamic Pricing for Airline Ancillaries with Customer Context. / Shukla, Naman; Kolbeinsson, Arinbjörn; Otwell, Ken; Marla, Lavanya; Yellepeddi, Kartik.

2019. 2174-2182 Paper presented at the 25th ACM SIGKDD International Conference, .

Research output: Contribution to conferencePaper

Shukla, N, Kolbeinsson, A, Otwell, K, Marla, L & Yellepeddi, K 2019, 'Dynamic Pricing for Airline Ancillaries with Customer Context' Paper presented at the 25th ACM SIGKDD International Conference, 8/4/19 - 8/8/19, pp. 2174-2182. https://doi.org/10.1145/3292500.3330746
Shukla N, Kolbeinsson A, Otwell K, Marla L, Yellepeddi K. Dynamic Pricing for Airline Ancillaries with Customer Context. 2019. Paper presented at the 25th ACM SIGKDD International Conference, . https://doi.org/10.1145/3292500.3330746
Shukla, Naman ; Kolbeinsson, Arinbjörn ; Otwell, Ken ; Marla, Lavanya ; Yellepeddi, Kartik. / Dynamic Pricing for Airline Ancillaries with Customer Context. Paper presented at the 25th ACM SIGKDD International Conference, .
@conference{5df7771f5fcf4f2396a1b65f12bb90ff,
title = "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.",
author = "Naman Shukla and Arinbj{\"o}rn Kolbeinsson and Ken Otwell and Lavanya Marla and Kartik Yellepeddi",
year = "2019",
doi = "10.1145/3292500.3330746",
language = "English (US)",
pages = "2174--2182",
note = "the 25th ACM SIGKDD International Conference ; Conference date: 04-08-2019 Through 08-08-2019",

}

TY - CONF

T1 - Dynamic Pricing for Airline Ancillaries with Customer Context

AU - Shukla, Naman

AU - Kolbeinsson, Arinbjörn

AU - Otwell, Ken

AU - Marla, Lavanya

AU - Yellepeddi, Kartik

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

U2 - 10.1145/3292500.3330746

DO - 10.1145/3292500.3330746

M3 - Paper

SP - 2174

EP - 2182

ER -