Forecasting requests based on context data for a network-based service
A network system can communicate with user and provider devices to facilitate the provision of a network-based service. The network system can identify optimal service providers to provide services requested by users. The network can utilize context data in matching service providers with users. In particular, the network system can determine, based on context data associated with a user, whether to perform pre-request matching for that user. A service provider who is pre-request matched with the user can be directed by the network system to relocate via a pre-request relocation direction. When the user submits the service request after the pre-request match, the network system can either automatically transmit an invitation to the pre-request matched service provider or can perform post-request matching to identify an optimal service provider for the user.
1. A computing system for managing a transport service, the computing system comprising:
one or more processors; and
one or more memory resources storing instructions that, when executed by the one or more processors of the computing system, cause the computing system to perform operations that include:
receiving, over one or more networks, context data from a first user device of a first user, the context data including a current location of the first user device and application activity data corresponding to user interactions with a user application operating on the first user device;
based at least in part on the context data, determining a likelihood that the first user will transmit a service request during a lookahead period that spans a future period of time;
in response to determining the likelihood that the first user will transmit a service request during a lookahead period, determining whether a first service provider is likely to fulfill the service request if the service request is transmitted from the first user device during the lookahead period;
wherein determining whether the first service provider is likely to fulfill the service request includes determining a propensity of either of the first user or the first service provider cancelling the service request after the first service provider has accepted an invitation for the service request;
based on determining that the first service provider is likely to fulfill the service request, matching the first service provider to the first user before the service request is transmitted from the first user device;
classifying the first service provider as unavailable for matching with other users during the lookahead period;
receiving, over the one or more networks, the service request for the transport service from the first user device during the lookahead period; and
based on the service request received from the first user device during the lookahead period, transmitting, to a first provider device of the first service provider, the invitation to provide transport for the first user.
2. The computing system of claim 1 , wherein the context data further includes, for the first user device, user device sensor data or user profile data.
3. The computing system of claim 1 , wherein the context data includes data that indicates a user application is executing in a background of the first user device.
4. The computing system of claim 1 , wherein determining the likelihood that the first user will transmit the service request includes determining a machine-learned context model, the machine-learned context model being based on historical data associated with the first provider device and the context data, and wherein the operations include using the machine-learned context model in determining to perform matching for the first service provider.
5. The computing system of claim 1 , wherein matching the first service provider to the first user is based at least in part on at least one of (i) a distance between the first service provider and the first user, or (ii) an estimated time of arrival of the first service provider to a location of the first user.
6. The computing system of claim 1 , wherein determining whether the first service provider is likely to fulfill the service request incudes determining a likelihood of the service provider accepting the invitation to transport the first user.
7. The computing system of claim 6 , wherein determining whether the first service provider is likely to fulfill the service request incudes determining, a likelihood of the first service provider canceling the service request.
8. The computing system of claim 1 , wherein the operations include:
determining the future period of time spanned by the lookahead period based at least in part on the context data.
9. The computing system of claim 8 , wherein the future period of time spanned by the lookahead period is determined dynamically, so that the lookahead period is specific to the context data received from the first user device.
10. A non-transitory computer-readable medium that stores instructions for managing a transport service, which when executed by one or more processors of a computing system, cause the computing system to perform operations that include:
receiving, over one or more networks, context data from a first user device of a first user, the context data including a current location of the first user device and application activity data corresponding to user interactions with a user application operating on the first user device;
based at least in part on the context data, determining a likelihood that the first user will transmit a service request during a lookahead period that spans a future period of time;
in response to determining the likelihood that the first user will transmit a service request during a lookahead period, determining whether a first service provider is likely to fulfill the service request if the service request is transmitted from the first user device during the lookahead period;
wherein determining whether the first service provider is likely to fulfill the service request includes determining a propensity of either of the first user or the first service provider cancelling the service request after the first service provider has accepted an invitation for the service request;
based on determining that the first service provider is likely to fulfill the service request, matching the first service provider to the first user before the service request is transmitted from the first user device;
classifying the first service provider as unavailable for matching with other users during the lookahead period;
receiving, over the one or more networks, the service request for the transport service from the first user device during the lookahead period; and
based on the service request received from the first user device during the lookahead period transmitting, to a first provider device of the first service provider, the invitation to provide transport for the first user.
11. The non-transitory computer-readable medium of claim 10 , wherein the context data further includes, for the first user device, user device sensor data or user profile data.
12. The non-transitory computer-readable medium of claim 10 , wherein the context data includes data that indicates a user application is executing in a background of the first user device.
13. The non-transitory computer-readable medium of claim 10 , wherein determining the likelihood that the first user will transmit the service request includes determining a machine-learned context model, the machine-learned context model being based on historical data associated with the first provider device and the context data, and wherein the operations include using the machine-learned context model in determining to perform matching for the first service provider.
14. The non-transitory computer-readable medium of claim 10 , wherein matching the first service provider to the first user is based at least in part on at least one of (i) a distance between the first service provider and the first user, or (ii) an estimated time of arrival of the first service provider to a location of the first user.
15. The non-transitory computer-readable medium of claim 10 , wherein determining whether the first service provider is likely to fulfill the service request incudes determining a likelihood of the service provider accepting the invitation to transport the first user.
16. The non-transitory computer-readable medium of claim 15 , wherein determining whether the first service provider is likely to fulfill the service request incudes determining, a likelihood of the first service provider canceling the service request.
17. The non-transitory computer-readable medium of claim 10 , wherein the operations include:
determining the future period of time spanned by the lookahead period based at least in part on the context data.
18. The non-transitory computer-readable medium of claim 17 , wherein the future period of time spanned by the lookahead period is determined dynamically, so that the lookahead period is specific to the context data received from the first user device.
19. A computer-implemented method for managing a transport service, the method comprising:
receiving, over one or more networks, context data from a first user device of a first user, the context data including a current location of the first user device and application activity data corresponding to user interactions with a user application operating on the first user device;
based at least in part on the context data, determining a likelihood that the first user will transmit a service request during a lookahead period that spans a future period of time;
in response to determining the likelihood that the first user will transmit a service request during a lookahead period, determining whether a first service provider is likely to fulfill the service request if the service request is transmitted from the first user device during the lookahead period;
wherein determining whether the first service provider is likely to fulfill the service request includes determining a propensity of either of the first user or the first service provider cancelling the service request after the first service provider has accepted an invitation for the service request;
based on determining that the first service provider is likely to fulfill the service request, matching the first service provider to the first user before the service request is transmitted from the first user device;
classifying the first service provider as unavailable for matching with other users during the lookahead period;
receiving, over the one or more networks, the service request for the transport service from the first user device during the lookahead period; and
based on the service request received from the first user device during the lookahead period transmitting, to a first provider device of the first service provider, the invitation to provide transport for the first user.
20. The computer-implemented method of claim 19 , wherein determining the likelihood that the first user will transmit the service request includes determining a machine-learned context model, the machine-learned context model being based on historical data associated with the first provider device and the context data, and wherein the method further comprises using the machine-learned context model in determining to perform matching for the first service provider.