As outlined in The Notification Problem, “watching” is a central part of Hopper’s product strategy. Watching a trip is a really useful tool for savvy travelers: It means they can go on living their lives while we do the heavy lifting of keeping an eye on their trips’ prices and notifying them when prices drop to our predicted low (as well as alerting them about good deals and flash sales). And for us, the feature has important engagement hooks, as users who watch a flight are much more likely to return to the app than those who do not.
…el a simple linear relationship with price (or some transformation of price) using a single weight. But it’s unclear that a monotonic relationship with price always makes sense when modeling user travel preferences. Certainly users prefer lower prices, all other things being equal, but often users are seeking to find the best trip they can get for some target budget. Other examples of continuous features where users often prefer an intermediate rather than extreme value include: length of stay, layover time, and flight duration or distance.
…se to treat itineraries independently from a user perspective. Indeed, Hopper’s raison d’être is to help users navigate the myriad potential tradeoffs between alternative flight and hotel options, based on each user’s unique constraints and perception of value vs price. This means that it’s important for us to model features that capture relationships between “product…