How data should improve your product

Excerpted (with edits) from How Airbnb used data to propel its growth to a $10B valuation by Max Song and Carl Shan:

Airbnb head of data science Riley Newman sees the collective data 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 teams.

Example: As a marketplace, search is at the heart of Airbnb’s matching. 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  Airbnb acquired more data 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: “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.”

Notes:
(1) Note the job description of a data scientist in a startup: To interpret data into actionable decisions for the product, marketing and customer support teams.
(2) Thank you Guy Cohen for the link.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s