Predicting customer purpose of travel in a low-cost travel environment—A Machine Learning Approach

Abstract

In the airline, business a passenger’s purpose of travel (business or leisure) has a strong relationship with the price elasticity of that passenger. Full-service network carriers (FSNCs) have long since recognized and monetized this concept by creating different cabins and products for the different types of customers. Conversely, until now, low-cost carriers (LCCs) have done little to differentiate between different types of customers. Recently though, even low-cost carriers have recognized the importance of the business travellers and are attempting to diversify their product offering to cater for different passenger requirements. In this paper, we use machine learning techniques to predict whether a passenger is travelling for business or leisure purposes. Although the problem is formulated as a prediction task, the primary objective is to model the behavioural differences between the two types of customers. In this respect, we discuss the importance and need for effective and interpretable machine learning techniques to facilitate communication with business stakeholders. This is a key requirement to improve the application and results obtained in research in daily practice, particularly in industries that are not primarily information technology based.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 12 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.