Automated determination of booking availability for user sourced accommodations
Methods and systems for updating a calendar entry for an accommodation listing are disclosed. In one embodiment, the method comprises generating an availability model and an acceptance model for an accommodation listing in an accommodation reservation system and determining based on those models the probability that the accommodation listing would be able to be booked. Furthermore, the result of an accommodation search query can be filtered and/or sorted using the determined probability of booking.
1. A computer implemented method, comprising:
identifying a plurality of past booking requests for accommodations listed by hosts on a reservation platform, each of the plurality of past booking requests having one or more temporal features;
receiving a search query from a guest for accommodation, the search query comprising a geographical location and a requested date range;
identifying a set of candidate accommodations in the geographical location that are not booked during the requested date range, each of the candidate accommodations associated with an availability calendar that is maintained by a host of the candidate accommodation and indicates that the candidate accommodation is not booked during the requested date range;
providing a user interface to the guest comprising identifiers of the set of candidate accommodations, the identifiers being sorted according to one or more default criteria;
detecting a selection by the guest of an option to re-sort the identifiers according to an availability criterion;
calculating, by applying a predictive computer model to the requested date range, a predicted availability that indicates a likelihood that each candidate accommodation of the set of candidate accommodations that is not booked during the requested date range according to the availability calendar is actually available for booking during the requested date range, the predictive computer model trained prior to receiving the search query based on values of a plurality of features of the past booking requests, the values at least partially relating to the one or more temporal features of each of the plurality of features;
ranking the set of candidate accommodations based at least on their respective predicted availabilities; and
updating the user interface to provide, to the guest, the identifiers as re-sorted according to the ranking.
2. The computer implemented method of claim 1 , wherein the past booking requests were made for a number of days in the past.
3. The computer implemented method of claim 1 , wherein the past booking requests were made at most a threshold number of days in the past.
4. The computer implemented method of claim 1 , wherein calculating the predicted availability is based on a day of a week for which the accommodation is requested.
5. The computer implemented method of claim 1 , wherein calculating the predicted availability is based on a month the accommodation is requested for.
6. The computer implemented method of claim 1 , wherein calculating the predicted availability is based on whether a day the accommodation was requested for is a holiday.
7. The computer-implemented method of claim 1 , further comprising, for each of the candidate accommodations, determining a probability of booking acceptance that indicates a likelihood that a booking request for the candidate accommodation will be accepted by the host of the accommodation in response to a booking request received from the guest, the probability of booking acceptance for the candidate accommodation being based upon the predicted availability for that candidate accommodation.
8. A system comprising:
a non-transitory computer-readable medium with instructions encoded thereon; and
one or more processors configured to, when executing the instructions, perform operations of:
identifying a plurality of past booking requests for accommodations listed by hosts on a reservation platform, each of the plurality of past booking requests having one or more temporal features;
receiving a search query from a guest for accommodation, the search query comprising a geographical location and a requested date range;
identifying a set of candidate accommodations in the geographical location that are not booked during the requested date range, each of the candidate accommodations associated with an availability calendar that is maintained by a host of the candidate accommodation and indicates that the candidate accommodation is not booked during the requested date range;
providing a user interface to the guest comprising identifiers of the set of candidate accommodations, the identifiers being sorted according to one or more default criteria;
detecting a selection by the guest of an option to re-sort the identifiers according to an availability criterion;
calculating, by applying the predictive computer model to the requested date range, a predicted availability that indicates a likelihood that each candidate accommodation of the set of candidate accommodations that is not booked during the requested date range according to the availability calendar is actually available for booking during the requested date range, the predictive computer model trained prior to receiving the search query based on values of a plurality of features of the past booking requests, the values at least partially relating to the one or more temporal features of each of the plurality of features;
ranking the set of candidate accommodations based at least on their respective predicted availabilities; and
updating the user interface to provide, to the guest, the identifiers as re-sorted according to the ranking.
9. The system of claim 8 , wherein the past booking requests were made for a number of days in the past.
10. The system of claim 8 , wherein the past booking requests were made at most a threshold number of days in the past.
11. The system of claim 8 , wherein calculating the predicted availability is based on a day of a week for which the accommodation is requested.
12. The system of claim 8 , wherein calculating the predicted availability is based on a month the accommodation is requested for.
13. The system of claim 8 , wherein calculating the predicted availability is based on whether a day the accommodation was requested for is a holiday.
14. The system of claim 8 , wherein the one or more processors is further configured, when executing the instructions to perform operations of, for each of the candidate accommodations, determining a probability of booking acceptance that indicates a likelihood that a booking request for the candidate accommodation will be accepted by the host of the accommodation in response to a booking request received from the guest, the probability of booking acceptance for the candidate accommodation being based upon the predicted availability for that candidate accommodation.
15. A computer program product comprising a non-transitory computer-readable storage medium containing computer program code, the computer program code when executed by one or more processors causes the one or more processors to perform operations, the computer program code comprising instructions to:
identify a plurality of past booking requests for accommodations listed by hosts on a reservation platform, each of the plurality of past booking requests having one or more temporal features;
receive a search query from a guest for accommodation, the search query comprising a geographical location and a requested date range;
identify a set of candidate accommodations in the geographical location that are not booked during the requested date range, each of the candidate accommodations associated with an availability calendar that is maintained by a host of the candidate accommodation and indicates that the candidate accommodation is not booked during the requested date range;
provide a user interface to the guest comprising identifiers of the set of candidate accommodations, the identifiers being sorted according to one or more default criteria;
detect a selection by the guest of an option to re-sort the identifiers according to an availability criterion;
calculate, by applying the predictive computer model to the requested date range, a predicted availability that indicates a likelihood that each candidate accommodation of the set of candidate accommodations that is not booked during the requested date range according to the availability calendar is actually available for booking during the requested date range, the predictive computer model trained prior to receiving the search query based on values of a plurality of features of the past booking requests, the values at least partially relating to the one or more temporal features of each of the plurality of features;
rank the set of candidate accommodations based at least on their respective predicted availabilities; and
update the user interface to provide, to the guest, the identifiers as re-sorted according to the ranking.
16. The computer program product of claim 15 , wherein the past booking requests were made for a number of days in the past.
17. The computer program product of claim 15 , wherein the past booking requests were made at most a threshold number of days in the past.
18. The computer program product of claim 15 , wherein calculating the predicted availability is based on a day of a week for which the accommodation is requested.
19. The computer program product of claim 15 , wherein calculating the predicted availability is based on a month the accommodation is requested for.
20. The computer program product of claim 15 , wherein calculating the predicted availability is based on whether a day the accommodation was requested for is a holiday.