Title: A machine learning approach to itinerary-level booking prediction in competitive airline markets

Authors: Daniel Hopman; Ger Koole; Rob Van Der Mei

Addresses: Department of Mathematics, Faculty of Sciences, Vrije Universiteit Amsterdam, De Boelelaan 1111, 1081HV, Amsterdam, The Netherlands ' Department of Mathematics, Faculty of Sciences, Vrije Universiteit Amsterdam, De Boelelaan 1111, 1081HV, Amsterdam, The Netherlands ' CWI, Stochastics, Science Park 123, 1098XG, Amsterdam, The Netherlands; Department of Mathematics, Faculty of Sciences, Vrije Universiteit Amsterdam, De Boelelaan 1111, 1081HV, Amsterdam, The Netherlands

Abstract: Demand forecasting is extremely important in revenue management. After all, it is one of the inputs to an optimisation method which aims to maximise revenue. Most, if not all, forecasting methods use historical data to forecast the future, disregarding the 'why'. In this paper, we combine data from multiple sources, including competitor data, pricing, social media, safety and airline reviews. Next, we study five competitor pricing movements that, we hypothesise, affect customer behaviour when presented with a set of itineraries. Using real airline data for ten different OD-pairs and by means of extreme gradient boosting, we show that customer behaviour can be categorised into price-sensitive, schedule-sensitive and comfort ODs. Through a simulation study, we show that this model produces forecasts that result in higher revenue than traditional, time series forecasts.

Keywords: demand forecasting; effects of competition; traditional statistics; machine learning.

DOI: 10.1504/IJRM.2021.120347

International Journal of Revenue Management, 2021 Vol.12 No.3/4, pp.153 - 191

Received: 17 Oct 2020
Accepted: 04 Mar 2021

Published online: 17 Jan 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article