The travel sector has arguably been slower than other industries to take up machine learning – a subset of the larger field of Artificial Intelligence – focusing on automation methods to learn and predict, from past data. Is it a cultural phenomenon? Perhaps. The travel industry is among most traditional of all in terms of its main selling point – the personalised, human-facing customer experience – and has struggled to come to terms with machines replacing human recommendation and action.
Today’s customer is seeking more answers, more quickly, from companies before and after buying products and services – and the modern traveller is no exception. Traditional travel firms need to move with the times and respond to customer expectations. Just witness the collapse of Thomas Cook in the UK this year as one example – the digital transformation of the travel industry was one of the main challenges to one of the world’s oldest travel companies. Today’s digitally literate customers – young as well as old – are not letting organisations sit and relax. Clued-up travellers are constantly comparing prices of flights, hotels, and car rentals to make sure that they get the best possible value and experience for their money.
The travel industry should not be fearful. According to a survey by booking.com, 29 per cent of travellers are happy letting a computer plan their next trip, while half say it doesn’t matter who is arranging their itinerary as long as all their questions are answered. Machine learning can assist companies to analyse customer profiles, their preferences and habits to offer a personalised product, solution and service, in this case a complete itinerary as well. With the amount of historic data available, it can also be leveraged to predict patterns as well as customer behaviour.
The transformation using machine-learning has already started. Google Flights, for example, is already one step ahead of airline companies by using machine learning to predict flight delays and announcing them before the companies, while to improve the travel experience at the airports, Delta airlines has introduced self-service baggage drop machines allowing travellers to quickly and securely check-in their bags. Additionally, they have coupled this with facial recognition technology, which can match the customers to their passport pictures. Such automation frees up the on ground agents, to focus on good customer service. Hopper, a travel start-up, helps customers to find the best time to book flights– it leverages machine learning and predictive analysis to identify whether the traveller should book the flights right now or wait for the price to drop in the future. Similarly, it also expanded this functionality to booking hotels as well, thus allowing customers to save money throughout the travel journey.
Meanwhile, the TUI Group has partnered with data-driven travel platform Utrip to introduce a personalised trip planning tool that asks travellers to rate their preferences across various categories such as ‘food and drink’, ‘shopping’ or ‘nature and adventure’, as well as purpose of their trip, tailoring holidays that will most suit that traveller, to help them steal a march on their rivals. The Dorchester hotel group uses machine learning to read 7,000 reviews on the likes of booking.com and TripAdvisor in less than a minute – even analysing the responses in terms of nuances of sarcasm or humour – allowing staff to understand in a nutshell what customers want from their stay. What is perhaps the most frustrating experience after a gruelling flight? Most would say probably the wait to check in at a hotel. The Marriott hotel chain has piloted facial recognition software for check-ins at two locations in China. The new kiosks will be able to scan and identify guests’ faces, pull up their reservations, and check them in – all without the help of humans – in about a minute.
At VFS Global, we understand the potential of machine learning and the benefits that it can provide throughout the visa processing value chain. To help the applicants with typically long application forms, we have piloted the first of the kind, machine learning enabled data extraction feature that identifies specific data points from various documents and auto populates the visa application form, cutting the time required to complete and application form by 50 per cent. ViVA, a visa service chatbot, was also trialled by VFS Global to provide highly-nuanced responses to applicant queries. The chatbot is advanced enough to think two steps ahead of the customer – if an applicant is trying to track their visa application, for instance, the chatbot can not only give them a status update, but can also potentially provide information they did not ask for, including pick-up or courier delivery options. And in terms of productivity and cost savings against humans, it is no contest: ViVA can handle 10,000 enquiries per second or 864 million enquiries in a day and is available 24/7. Examples like these show that the travel industry should not be afraid of machine learning. In fact, it can help enhance the personal service offering, as it can cut time on mundane tasks and release employees to undertake more creative and customer serving activities. And that, after all, is what we’re all in the travel industry for.