Let’s imagine for a moment that you’ve arrived at a great hotel you picked up after comparing prices on your favorite travel app. As you drop off your luggage, the app proactively suggests a few perfect spots to eat nearby.
It knows it’s getting close to lunchtime and that you love sushi. You finish your spicy tuna roll and pay for the meal by tapping your phone screen.
The app quickly notifies you about impending rain storm and suggests that you switch that bike tour you were planning to a top-rated portrait gallery that had caught your eye the day before—a good way to have fun and stay dry.
“Would you like to confirm your skip-the-line tour? You’ll get 30 per cent off if you book now,” it says in a soothing voice.
All of this is theoretically possible in the not-too-distant future through the power of machine learning, an application of artificial intelligence that can be used to offer more personalised and contextual recommendations.
Or at least, that’s the predictions after new research from TripAdvisor.
The effect of machine learning robots will undoubtedly be felt in the travel industry; however, it remains to be seen whether it will have positive or negative effects.
Not to miss out on a good thing, TripAdvisor has been testing a machine learning offering for some time, launching its ‘Just for You’ feature in 2014, which ranked hotels based on each user’s personal preferences, shopping behavior and past reviews.
While the benefits of machine learning systems can be easily implemented in other industries – Netflix and Amazon’s suggested tabs – it poses a bit more difficulty to travel.
For TripAdvisor, the biggest hurdle is accepting the unpredictability of travel. In its latest report on the subject, the company cited the “unique challenges” the industry faces in taking on the tech.
“If your streaming video service recommends a bad movie, then the viewer has lost, at worst, a couple hours of time. But, if a travel site recommends the wrong place to stay or things to do, then the opportunity cost is potentially much greater when you consider the wasted time and money,” the report said.
So how has the travel giant utilised machines learning to its advantage?
3 Machine Learning Lessons in Travel
- Lesson #1: Travel Personas Vary
The process of making contextual recommendations in travel is more challenging than in many other industries. That’s because a person’s travel persona can change quite a bit depending on the type of trip they take and with whom they are travelling.
Think of how differently you travel during a business trip, as compared to a romantic trip with your partner or with kids. That cozy boutique B&B that’s perfect for one type of getaway might be a complete disaster for the next.
For this reason, TripAdvisor worked to better understand how to adapt recommendations based on the context of a person’s trip, becoming more intuitive and personalised.
- Lesson #2: Recommendations are Best When You Consider Both Implicit and Explicit Signals
Consumers want and need to be able to explicitly provide even stronger signals about what kind of trip or experience they want or change their preferences as needed.
For that reason, it’s important to give travellers the ability to filter and refine personalised recommendations based on machine learning.
- Lesson #3: Personalised Recommendations Benefit Travellers and Businesses Alike
TripAdvisor has clued into the fact that the ranking of top rated hotels is not always most helpful to travellers, as the highest ranked properties in a given destination may not always align to a particular traveller’s needs or search queries.
For example, the best hotel in the city might break the traveller’s bank or lack availability for the dates searched. Machine learning has helped offer smarter sorting tailored to the needs of each user.
TripAdvisor’s Head of Worldwide Product Development, Adam Medros, added, “We’ve also baked machine learning into new “Things to Do” and “Restaurants” categories to offer more personalised and contextual recommendations.
“Let’s say it’s early in the morning and you’re exploring a new city, we now intuitively recommend a great breakfast spot nearby. That advantage is that you no longer need to proactively perform that query—it’s already done for you.
“Or, if you’re looking for a great hamburger, we don’t just suggest spots that happen to have burgers; we recommend the best restaurants for burgers. A small but important distinction.
“It’s the difference between a French restaurant and a place that serves French bread, and machine learning is helping to make those distinctions in new and exciting ways.”
What does the future hold?
- Personalised – Travel recommendations will be increasingly tailored to the individual
- Contextual – Suggestions about where to go and what to do will be based ever more on what type of trip you’re on, where you are, the time of day and the weather outside
- Automated – The amount of input a user needs to provide will gradually decline
- Assistive – Travel recommendations will be increasingly based on passive information based on proactive queries
- Comprehensive – Every aspect of the trip and ancillary services will be combined in unique and super helpful ways