Airbnb – for the few people not familiar yet 😉 – is an online marketplace that matches people who rent out their homes (‘hosts’) with people who are looking for a place to stay (‘guests’). Airbnb uses controlled experiments to learn and make decisions at every step of product development, from design to algorithms. They are equally important in shaping the user experience.
Hypothesis
Changing the maximum value of the price filter on the search page from $300 to $1000 will increase the number of bookings
Results
After 36 days the test proofed insignificant (p-value 0.4). Note that after 7 days the test was significant.
Learnings
Airbnb learned that the behaviour of ‘early bookers’ – people that decide in within a few days – is quite different. If you include the complete population (early, average & late bookers) the filter did not make a difference.
Airbnb still decided to implement the larger price range. Certain users like the ability to search for high-end places and there was negative impact on the metrics.
Even though the design has changed again – the max price range of €1000 is still there (July 2016)

Test details
Test element |
Selection
|
Page type |
All |
Test date |
May 2014 |
Website information