Granted Patent B2

US 10,572,833 · App. 16/358,393 · Granted Feb 25, 2020

Abstract

Claims (69)

1. A computer implemented method, comprising:

receiving from a guest computer, a search query that specifies a request feature;

in response to receiving the search query, identifying a plurality of listings for accommodations;

accessing a plurality of reservation requests received for the plurality of listings, each reservation request in a subset of the plurality of reservation requests having previously been accepted by a host computer from which the listing originated;

determining a cluster preference value based on the plurality of reservation requests;

generating a plurality of preference models, each respective preference model of the plurality of preference models corresponding to each listing of the plurality of listings, wherein generating each respective preference model of the plurality of preference models corresponding to each listing of the plurality of listings comprises:

determining a listing-specific preference value for the request feature based on the cluster preference value and a preference value specific to the listing of the plurality of listings for the request feature, and

generating the respective preference model corresponding to the listing of the plurality of listings based on the listing-specific preference value;

applying each respective preference model of the plurality of preference models to a prospective reservation request for the listing corresponding to the respective preference model and associated with the search query to compute a probability that the prospective reservation request will be accepted by the corresponding host computer;

ranking the plurality of listings based on the computed probabilities; and

transmitting search results corresponding to the plurality of listings to the guest computer for display based on the ranking.

2. The method of claim 1 , wherein determining the cluster preference value based on the plurality of reservation requests comprises:

determining a number of reservation requests in the plurality of reservation requests that were accepted;

determining a number of reservation requests in the plurality of reservation requests that possess the request feature; and

determining the cluster preference value based on the number of the reservation requests that were accepted and the number of the reservation requests that possess the request feature.

3. The method of claim 1 , wherein a respective preference model for a listing of the plurality of listings comprises parameters that identify a relationship between the request feature and a reservation request for the listing being accepted or rejected by the corresponding host computer.

4. The method of claim 1 , wherein the plurality of listings are associated with a same attribute selected from at least one of a geographical region, a room type, and a host.

5. The method of claim 1 , wherein the request feature indicates a mechanism for classifying the plurality of reservation requests.

6. The method of claim 1 , wherein determining the listing-specific preference value comprises:

identifying a subset of the plurality of reservation requests that were received for the listing;

determining a number of the reservation requests in the subset that were accepted and a number of the reservation requests in the subset that possess the request feature; and

determining the listing-specific preference value based on a combination of the cluster preference value, the number of the reservation requests in the subset that were accepted and the number of the reservation requests in the subset that possess the request feature.

7. The method of claim 1 , wherein generating the preference model comprises generating a training data set by applying the listing-specific preference value to a subset of the plurality of reservation requests that were received for the listing.

8. The method of claim 1 , wherein the request feature is a gap feature indicating a specific period of time between a previous reservation or calendar unavailability of the accommodation ending and a reservation associated with a reservation request beginning.

9. A non-transitory computer readable medium storing executable computer program instructions, the computer program instructions comprising instructions that when executed cause a computer processor to:

receive from a guest computer, a search query that specifies a request feature;

in response to receiving the search query, identify a plurality of listings for accommodations;

access a plurality of reservation requests received for the plurality of listings, each reservation request in a subset of the plurality of reservation requests having previously been accepted by a host computer from which the listing originated;

determine a cluster preference value based on the plurality of reservation requests;

generate a plurality of preference models, each respective preference model of the plurality of preference models corresponding to each listing of the plurality of listings, wherein the computer program instructions for generating each respective preference model of the plurality of preference models corresponding to each listing of the plurality of listings comprise instructions that when executed cause the computer processor to:

determine a listing-specific preference value for the request feature based on the cluster preference value and a preference value specific to the listing of the plurality of listings for the request feature, and

generate the respective preference model corresponding to the listing of the plurality of listings based on the listing-specific preference value;

apply each respective preference model of the plurality of preference models to a prospective reservation request for the listing corresponding to the respective preference model and associated with the search query to compute a probability that the prospective reservation request will be accepted by the corresponding host computer;

rank the plurality of listings based on the computed probabilities; and

transmit search results corresponding to the plurality of listings to the guest computer for display based on the ranking.

10. The computer readable medium of claim 9 , wherein the computer program instructions for determining the cluster preference value based on the plurality of reservation requests comprise instructions that when executed cause the computer processor to:

determine a number of reservation requests in the plurality of reservation requests that were accepted;

determine a number of reservation requests in the plurality of reservation requests that possess the request feature; and

determine the cluster preference value based on the number of the reservation requests that were accepted and the number of the reservation requests that possess the request feature.

11. The computer readable medium of claim 9 , wherein a respective preference model for a listing of the plurality of listings comprises parameters that identify a relationship between the request feature and a reservation request for the listing being accepted or rejected by the corresponding host computer.

12. The computer readable medium of claim 9 , wherein the plurality of listings are associated with a same attribute selected from at least one of a geographical region, a room type, and a host.

13. The computer readable medium of claim 9 , wherein the request feature indicates a mechanism for classifying the plurality of reservation requests.

14. The computer readable medium of claim 9 , wherein the computer program instructions for determining the listing-specific preference value comprise instructions that when executed cause the computer processor to:

identify a subset of the plurality of reservation requests that were received for the listing;

determine a number of the reservation requests in the subset that were accepted and a number of the reservation requests in the subset that possess the request feature; and

determine the listing-specific preference value based on a combination of the cluster preference value, the number of the reservation requests in the subset that were accepted and the number of the reservation requests in the subset that possess the request feature.

15. The computer readable medium of claim 9 , wherein the computer program instructions for generating the preference model comprise instructions that when executed cause the computer processor to generate a training data set by applying the listing-specific preference value to a subset of the plurality of reservation requests that were received for the listing.

16. A computer system comprising:

a non-transitory computer-readable storage medium storing executable computer program instructions, the computer program instructions comprising instructions that when executed cause a computer processor to perform steps comprising:

receiving from a guest computer, a search query that specifies a request feature;

in response to receiving the search query, identifying a plurality of listings for accommodations;

accessing a plurality of reservation requests received for the plurality of listings, each reservation request in a subset of the plurality of reservation requests having previously been accepted by a host computer from which the listing originated;

determining a cluster preference value based on the plurality of reservation requests;

generating a plurality of preference models, each respective preference model of the plurality of preference models corresponding to each listing of the plurality of listings, wherein generating each respective preference model of the plurality of preference models corresponding to each listing of the plurality of listings comprises:

determining a listing-specific preference value for the request feature based on the cluster preference value and a preference value specific to the listing of the plurality of listings for the request feature, and

generating the respective preference model corresponding to the listing of the plurality of listings based on the listing-specific preference value;

applying each respective preference model of the plurality of preference models to a prospective reservation request for the listing corresponding to the respective preference model and associated with the search query to compute a probability that the prospective reservation request will be accepted by the corresponding host computer;

ranking the plurality of listings based on the computed probabilities; and

transmitting search results corresponding to the plurality of listings to the guest computer for display based on the ranking.

17. The computer system of claim 16 , wherein determining the cluster preference value based on the plurality of reservation requests comprises:

determining a number of reservation requests in the plurality of reservation requests that were accepted;

determining a number of reservation requests in the plurality of reservation requests that possess the request feature; and

determining the cluster preference value based on the number of the reservation requests that were accepted and the number of the reservation requests that possess the request feature.

18. The computer system of claim 16 , wherein a respective preference model for a listing of the plurality of listings comprises parameters that identify a relationship between the request feature and a reservation request for the listing being accepted or rejected by the corresponding host computer.

19. The computer system of claim 16 , wherein the plurality of listings are associated with a same attribute selected from at least one of a geographical region, a room type, and a host.

20. The computer system of claim 16 , wherein determining the listing-specific preference value comprises:

identifying a subset of the plurality of reservation requests that were received for the listing;

determining a number of the reservation requests in the subset that were accepted and a number of the reservation requests in the subset that possess the request feature; and

determining the listing-specific preference value based on a combination of the cluster preference value, the number of the reservation requests in the subset that were accepted and the number of the reservation requests in the subset that possess the request feature.

Assignments (7)