(Some of the)
Ensuring that what you see is what you’ll get
Finding the best itinerary for your needs
Inspiring you to travel to new places
Connecting partners with the right travellers
Go and try our Facebook bot J
Keeping you informed, finding the best time to buy
Can we do
Historical price focus
Price is only one feature that could make a destination attractive.
Sparse user data
Travel is (relatively) low frequency. Many new, anonymous users –
cold start problem in recommendation.
Destinations are relative
London from Edinburgh is not the same as London from NewYork.
No collaborative filtering (yet)
Traditional collaborative filtering algorithms are not suitable for the
data that we have.
No manual intervention
Many approaches that tackle cold-start require manual intervention
from users: profiles, surveys, tags, preferences.
No offline evaluation (yet)
Without data, we have no robust approaches to estimating the
accuracy of recommendations offline (e.g., RMSE).
Write the code: The architecture behind Skyscanner’s
recommended destinations (by @AndreBarbosa88)
Many ways to
define three key
Where do people want to (always, recently) go?
What is in higher demand where you are?
Destination-frequency, inverse global frequency.
Temporal shifts in search behaviours to capture
seasonality, events, demand.
“Design like you’re right, test like you’re wrong” by @MCFRL