AirBnB has over 4.5M property listings and hosts. When a consumer requests to stay at a property, the host reviews the request and can choose to accept or reject. Some hosts try to maximise occupancy and prefer stays that result in lots of short gaps that can be hard to fill. Some hosts are not interested in maximising their occupancy and would rather host infrequently. Host preferences seem to vary between big and small markets. And some hosts prefer far in advance bookings to just in time.
The project focused on identifying key trip characteristics that might predict the hosts preference for a stay or not. They were challenged by relative sparse data-sets but "evaluated the experiment by looking at multiple metrics, but the most important one was the likelihood that a guest requesting accommodation would get a booking (booking conversion)." "All these findings pointed to the same conclusion: if we could promote in our search results hosts who would be more likely to accept an accommodation request resulting from that search query, we would expect to see happier guests and hosts and more matches that turned into fun vacations (or productive business trips)." When "looked at listings from big and small markets separately, I found that they behaved quite differently. Hosts in big markets care a lot about their occupancy — a request with no gaps is almost 6% likelier to be accepted than one with 7 gap nights. For small markets I found the opposite effect; hosts prefer to have a small number of nights between requests. So, hosts in different markets have different preferences, but it seems likely that even within a market hosts may prefer different stays." "We could personalize our search results, but not in the way you might expect. Typically personalized search results promote results that would fit the unique preferences of the searcher — the guest. At a two-sided marketplace like Airbnb, we also wanted to personalize search by the preference of the hosts whose listings would appear in the search results."
L-2 regularized logistic regression was used to create predictions for host acceptance of a consumer request.
There were multiple iterations to determine the most important trip characteristics to predict acceptance.
AirBnB reports the following results: * 21% increase in Similar Listing carousel click-through-rate * 4.9% more guests discovering the listing they ended up booking in the Similar Listing carousel