In our latest analysis, we address one of the key challenges in airline route strategy. Before setting up a new route and making a decision there are a number of assumptions that airlines must make. Having a more scientific approach that would help to predict how new Origin & Destination routes are likely to behave and bring benefits to the planning process. Therefore, in our report, we demonstrate how Artificial Intelligence – in this case a fairly simple formula called the K-means algorithm* can be applied to flight search data to help airlines gain a significant advantage in how they evaluate routes in order to make better informed decisions.
To research, we used datasets** that are available in our Travel Insight, analysing the search patterns of over 50,000 origins and destinations during 2016.
Here are some high-level observations from the data:
Long summer family holidays represent the largest grouping as more Origins and Destinations than any other come under this group. Usually, these routes are mainly for travel during summer months and they have weekend departures and at least one child is part of the booking.
The study also revealed that while geography matters, proximity to origin country dictates behaviour more than a preference for the destination country. For example, Faro (FAO) acts similarly to Algiers (ALG) and are grouped in the same cluster. Both destinations are popular during the winter time with mid-week departures. They are relatively similar in distance yet would perhaps not be the first two places to be grouped together in a traditional assumption.
We found that traditional ‘romantic couples’ city break destinations are equally popular with single travellers. Therefore, it means that since ‘solo trips’ and ‘share of couples’ categories are always allocated to the same clusters, there is no ‘typical’ couple’s destination. For example, Venice behaves similarly to other destinations with a high share of couples, but also has a similarly high share of travellers visiting this destination as part of a solo trip.
Click below to take a look at the full story and analysis and have a closer look at the full results of the analysis in the dashboard.
*Our approach to the study is based on a Python-based K-means algorithm, which is an unsupervised machine learning algorithm. If you want to understand the in’s and out’s of the K means algorithm you can watch this video here.
**The data set is based on global searches taking place on Skyscanner throughout 2016, including over 50,000 Origins and Destinations.