# Learning Cheap and Novel Flight Itineraries

## TL;DR

This paper presents a machine learning approach to efficiently generate affordable and novel round trip flight itineraries by combining airline legs, improving prediction accuracy and practical deployment in a travel platform.

## Contribution

The paper introduces a supervised learning model with location embeddings for constructing cheap flight itineraries, addressing the trade-off between recall and computational costs.

## Key findings

- Achieved an AUC of 80.48 with the proposed model
- Identified that 30% of airlines contribute most to cheap itineraries
- Model deployment improved user savings and satisfaction

## Abstract

We consider the problem of efficiently constructing cheap and novel round trip flight itineraries by combining legs from different airlines. We analyse the factors that contribute towards the price of such itineraries and find that many result from the combination of just 30% of airlines and that the closer the departure of such itineraries is to the user's search date the more likely they are to be cheaper than the tickets from one airline. We use these insights to formulate the problem as a trade-off between the recall of cheap itinerary constructions and the costs associated with building them. We propose a supervised learning solution with location embeddings which achieves an AUC=80.48, a substantial improvement over simpler baselines. We discuss various practical considerations for dealing with the staleness and the stability of the model and present the design of the machine learning pipeline. Finally, we present an analysis of the model's performance in production and its impact on Skyscanner's users.