How Airbnb used data to propel its growth to a $10B valuation

Whether you are part of a fast growing startup or an established company, choosing what part of the product to focus on is absolutely crucial to the success of your venture.

Above: Riley Newman

In an interview with Riley Newman, head of data science at Airbnb, we learned a valuable framework in thinking about concrete ways that data science helped prioritize product decisions and power Airbnb’s tremendous growth. The lessons he shared can help you drive your company’s data and product decisions to achieve an uplift in growth.

Editor’s note: Newman is speaking this Monday at DataBeat on decreasing customer support inquiries. It’s not too late to get tickets!

Data Is The Voice of Your Customer

At Airbnb, Riley sees the collective data is seen as the “voice” of the customer. Data scientists serve as the megaphone that amplifies the voice of the customer by teasing out their desires from the logs of customer interaction, and interpreting them into actionable decisions for the product, marketing and customer support team.

As Riley describes eloquently:

Data is the voice of your customer. Data is effectively a record of an action someone in your community performed, which represents a decision they made about what to do (or not) with your product. Data scientists can translate those decisions to stories that others can understand.

Improving Search

To illustrate the power of listening to the voice of the customer, let’s take a look at a specific example of how Airbnb used data to improve its product.

As a marketplace, search is at the heart of Airbnb’s matching. Careful tuning of this engine is a critical driver to accelerating growth and delighting customers.

However, in the beginning, Airbnb didn’t know what kind of guidance to give customers. So they started with a simple solution, returning “the highest quality set of listings within a certain radius from the center of wherever someone searched.”

Then, as more people came to use the site, Airbnb acquired more data. Eventually they found that by substituting their initial model with a user-data driven one, they were able to see an increase in customer bookings and satisfaction, as Riley describes:

So we decided to let our community solve the problem for us. Using a rich dataset comprised of guest and host interactions, we built a model that estimated a conditional probability of booking in a location, given where the person searched. A search for San Francisco would thus skew towards neighborhoods where people who also search for San Francisco typically wind up booking, for example the Mission District or Lower Haight.

By tapping into the data generated by their community, Airbnb found the answer to delivering a better product.

(You can read about the evolution of the models in full data-driven glory here).

Driving Company Growth

Another example of listening to the customer is how Airbnb used data to tailor their experience to different demographics, driving growth. Riley explained to us:

Getting back to the concept of data being the voice of the customer … when [users] come to our site [there’s] a lot of A/B testing here, looking for ways to make it more intuitive and satisfying to a person of any demographic, anywhere in the world.

As an example, in early 2014 Airbnb discovered that users from certain Asian countries tended to have a high bounce rate when visiting the home page. It soon became clear in the data that these users were being distracted by clicking on the “Neighborhood” link, and becoming lost in the photos — never to return to the booking.

A data scientist took a deep dive into this problem, and presented his findings to the engineering team, who tailored a redesign. For users from these countries, Airbnb removed the “Neighborhood” links and instead showcased the top traveling destinations in China, Korea, Japan and Singapore.

As a result, Airbnb saw more than a 10 percent lift in user conversion from their Asian visitors!

Conclusion

By plunging into their data, Airbnb was able to spot huge opportunities for growth and product improvement. Their combination of data smarts and entrepreneurial savviness catapulted them to a $10 billion valuation, millions of users around the world, and has left valuable lessons for the rest of us for thinking about data.

The bottom line: treat your data as the voice of your customer — use your data scientists to decipher what they are saying — and make the product decisions that will drive the bottom line through the ceiling!

More opportunities: Having data is not enough, knowing how to use it in the right way is really the key to having a successful data science team. If you want to learn more from Riley Newman, he is speaking this Monday at DataBeat on Decreasing Customer Support inbounds. Go see him and the other amazing speakers at this Monday and Tuesday!

Also, if you liked this interview and thought the lessons in data science were useful, sign up to be notified of when we launch The Data Science Handbook — a compilation of 25 powerful interviews with data scientists on the front lines: detailing how they got to data science, how they leverage data to make amazing products, and important lessons that they learned along the way.

You can get in touch with the authors to learn more about The Data Science Handbook by emailing data@datasciencehandbook.org.

About the authors: