How Airbnb uses AI to transform the travel industry

Unless you have been living under a rock, you might have heard of Airbnb or perhaps you have even used it. It is a popular online platform that aims to connect travellers who are looking for accommodation with hosts around the world. It was founded by two designers, Brian Chesky and Joe Gebbia in 2007.

The story is that the two designers were broke, and they were looking to raise money to pay their rent in San Francisco. So, they turned their apartment into a mini-bed and breakfast and rented out to attendees of a conference who could not find accommodation in hotels nearby.  It is from this that they came up with the name Airbnb, that stands for Air Bed and Breakfast. Little did they know that their concept would disrupt the travel and hospital industry! 

Airbnb Growth Facts  

So, how many people use Airbnb experiences?

Airbnb has grown in leaps and bounds since 2008.  According to Airbnb fast facts, at the time of this writing: 

• There are more than 7 Million listings 
• 100,000 plus cities with Airbnb listings
• 220,000 plus countries and regions with Airbnb listings
• Over 500Million guests have used Airbnb
• There over 400,000 plus experiences within 1000 plus cities since it was launched in 2016. 

With the millions of listing on Airbnb, you could be wondering how Airbnb sifts through the listing to provide the guest with the most perfect match and provide a personalized experience to its customers. 

Well, for Airbnb, Artificial Intelligence is an integral part of their system and it has powered them to deliver offerings and services to its users quite effectively.

How does Airbnb use AI?

Airbnb is one of the companies that are on the forefront of using new technologies like Artificial Intelligence and Machine learning in several ways from improving search to preventing fraud, to helping hosts optimize pricing. Here a few examples of how Airbnb utilizes AI: 

• Improving Search Rankings

The first thing when a guest lands on the Airbnb platform is to search for listing or experience within a city or region and in turn, Airbnb ranks the best match. In the past, Airbnb used to determine rankings based on data like date of your trip, duration and price. Today Airbnb uses AI-powered search algorithms by seeing similarities of places you click on, the places you view, host preferences, guest preferences to rank the most likely listings that you are likely to book. Airbnb says that they look at more than 100 factors to determine how the listing appears in the search results. 

• Calculating Prices

Initially, hosts had a challenge of determining prices for their properties and experiences. Airbnb came up with AI prediction models for predicting pricing and optimizing prices using variables like seasons, hotel rates, local events, pricing of homes in that area among others. 

“You might not see on the guest side, but for host suggestions…there’s lots of information about how many people are looking for your kind of home in that area, comparisons to other homes, and the probability that you’ll get a booking.”  Says Elena Grewal, Head of Data Science at Airbnb.

• Discovering and classifying in-app Messages

Within the Airbnb platform, hosts and guests use the messaging app to discuss more details on the bookings, payments methods, cancellations, refunds, trip planning and sharing experiences. Guests do expect an immediate response but at times the host may be busy or offline and it takes time to get a response.

In a bid to curb this problem, Airbnb has leveraged conversational AI technologies, — the Shared Products, Applied Machine Learning, and Machine Learning Infrastructure to provide real-time communication by communicating the intent of the message. This conversational AI algorithm can predict customers concerns, guide users through cancellation and refund process and also improve their experiences like recommending hotels nearby.

Within the Airbnb platform, hosts and guests use the messaging app to discuss more details on the bookings, payments methods, cancellations, refunds, trip planning and sharing experiences. Guests do expect an immediate response but at times the host may be busy or offline and it takes time to get a response.

In a bid to curb this problem, Airbnb has leveraged conversational AI technologies, — the Shared Products, Applied ML , and ML Infrastructure to provide real-time communication by communicating the intent of the message. This conversational AI algorithm can predict customers concerns, guide users through cancellation and refund process. Also, it helps improve their experiences like recommending hotels nearby.

• Analysing Guest Behaviour

Airbnb is also utilizing AI to analyse guest’s social media posts and criminals’ records to determine their trustworthiness.  According to Evening Standard, Airbnb uses a “software to scan sites including social media for traits such as “conscientiousness and openness” against the usual credit and identity checks and what it describes as “secure third-party databases”. Traits such as “neuroticism and involvement in crimes” and “narcissism, Machiavellianism, or psychopathy” are “perceived as untrustworthy”. 

This trait analyser is beneficial to hosts since they are assured of their personal safety and their property safety.

Why does it Matter

By looking at how Airbnb deploys AI to improve its business model shows us the importance of implementing AI in our business. It is effective, it improves the customer’s experience, assures clients and hosts of safety and it also improves search and discoverability of listings and experiences.

Check out our Masterclasses, to learn about how your business or organization can tap into data, AI and Machine learning in Kenya.
Airbnb Machine Learning