AI Is Powering Airbnb to Your Benefit
Wed, April 14, 2021

AI Is Powering Airbnb to Your Benefit

Airbnb operates in more than 81,000 cities and 191 countries across the world. It provides more than five million spaces to stay and offers unprecedented access to local interests / Photo by: Peter Ksinan via 123RF

 

In 2007, Brian Chesky and Joe Gebbia were looking for a way to raise money since they were having trouble paying their rent. They noticed that all hotel rooms in the city were booked. The youngsters saw this opportunity to put up a business. Thus, Chesky and Gebbia decided to rent out air mattresses in their apartment and called their service “Air Bed and Breakfast.” Little did they know that this small experiment would grow more than three million lodgings in 191 countries.

Air Bed and Breakfast was later on called Airbnb. MuchNeeded.com, a place where you get much-needed advice for your purchase decisions in the form of top-rated roundups and product reviews, reported that Airbnb operates in more than 81,000 cities and 191 countries across the world. It provides more than five million spaces to stay and offers unprecedented access to local interests. Today, more than 260 million guests have booked and stayed in Airbnb properties worldwide.

A 2016 study discovered that 49% of users of the home-sharing service used it as an alternative to a traditional hotel – up from 41% in 2015. The respondents stated that they have used Airbnb to replace beds and breakfasts, extended stay hotels, vacation rental sites, and corporate apartments. Another report showed that 19% of leisure travelers in 2016 had used Airbnb in the past 12 months while 18% of business travelers had done the same. During the same year, Airbnb occupied about 4% of traditional hotel demand.

The findings of the study revealed that 93% of the travelers who used Airbnb in 2016 were satisfied with the service they got – up from 90% in 2015. About 53% of the respondents stated that they use Airbnb because of the cost savings; 33% use it because of the authentic experience; 30% use it because of the location, and 28% use it because of the easy to use site/app. Recent statistics also showed that Airbnb’s value worldwide has reached $38 billion.

What most users don’t know is that Airbnb utilized artificial intelligence and machine learning to solve a problem that was plaguing them: effectively connecting travelers and hosts. The company also uses these technologies to keep up with the increasing demand for bookings and keep their customers safe.

Personalized Search Rankings

When Airbnb started, search rankings were identified based on a small number of hard-coded variables such as the price, duration, and dates of your trip. But as the company grew, it gathered huge amounts of data from its users that could be utilized to predict listing references. A study published on the preprint server Arxiv.org showed how Airbnb’s web and mobile app have improved the relevance of search results.

According to VentureBeat, an American technology website that helps business leaders make smarter decisions with its industry-leading AI and gaming coverage, Airbnb uses an “ecosystem” of algorithms instead of just one AI system. One of the algorithms Airbnb is using is LambdaRank, an algorithm that applies supervised machine learning to solve ranking problems. It has over 195 features, including taking into account the price, amenities, and historical booking count.

When Airbnb started, search rankings were identified based on a small number of hard-coded variables such as the price, duration, and dates of your trip. But as the company grew, it gathered huge amounts of data from its users that could be utilized to predict listing references / Photo by: baloon111 via 123RF

 

“The application to search ranking is one of the biggest machine learning success stories at Airbnb. Much of the initial gains were driven by a gradient boosted decision tree model. The gains, however, plateaued over time. This paper discusses the work done in applying neural networks in an attempt to break out of that plateau,” the authors wrote. 

The algorithms work by finding similarities in the places you click on, how long you look at them and the places you look at in the most depth. After that, they re-rank search results to find the places Airbnb thinks you’re most likely to stay in. Mike Curtis, the company’s VP of engineering, stated that they can show the customers the listings first that can give them the best experience offline. 

“It works for us because we don’t just want to get a booking for the sake of a booking; we want you to book something which is a great experience,” Curtis added. 

Keeping Customers Safe

Last October 2019, five people were killed at an Airbnb in California. Reports show that hosts have also been accusing guests of incurring millions of dollars in damage. To address this problem, Airbnb CEO Chesky announced in a tweet that the company would be banning ‘party houses’. They are also planning to redouble their efforts to combat unauthorized parties and get rid of abusive host and guest conduct. To effectively implement this, Airbnb will be using an AI-based background check tool developed by Trooly, a startup acquired by Airbnb in 2017. 

The tool is programmed to conduct background checks on potential clients by scanning search engines, social media, blogs, and other publicly available information. According to Business Insider, a fast-growing business site with deep financial, media, tech, and other industry verticals, it can also detect illegal activity and scan for traits including neuroticism, narcissism, Machiavellianism, or psychopathy. At the same time, it can detect online activities linked to drugs, alcoholism, prostitution and hate websites. Airbnb will also be using the AI tool to identify fake social media accounts. 

“Every Airbnb reservation is scored for risk before it’s confirmed. We use predictive analytics and machine learning to instantly evaluate hundreds of signals that help us flag and investigate suspicious activity before it happens,” Airbnb said on its website. 

Aside from this tool, Airbnb is also using other ways to screen renters. For instance, they screen all hosts and guests globally against regulatory, terrorist, and sanctions watch lists. They run background checks for US residents to look for prior felony convictions, sex offender registrations, and significant misdemeanors. Also, they are working with governments across the world to identify where they can do more background checks. According to Medical Daily, a medical and nutrition news website, the tool conducts a “deep internet search” where it finds find news articles mentioning their names. It can even see how potential customers treat others in real life by checking social connections, work history, and educational background.

The way Airbnb is using AI to satisfy their customers and keep them safe is a great application of machine learning by a huge business. The company is utilizing new technologies to enhance the experiences of their guests and hosts as well as address problems/issues. 

The way Airbnb is using AI to satisfy their customers and keep them safe is a great application of machine learning by a huge business / Photo by: lightfieldstudios via 123RF