DETERMINING DISUTILITY OF SHARED TRANSPORTATION REQUESTS FOR A TRANSPORTATION MATCHING SYSTEM
This disclosure covers computer-implemented methods, non-transitory computer readable media, and systems that determine disutility metrics for transportation requests in a shared transportation. For example, the disclosed systems determine estimated service metrics for a plurality of combinations of one or more transportation requests in the shared transportation (e.g., an estimated amount of time to perform a transportation service for a combination of one or more transportation requests). Additionally, the disclosed systems analyze the estimated service metrics to determine an effect of the transportation requests on a combined service metric for the shared transportation and then determine disutility metrics for the transportation requests based on the determined effect. The disclosed systems then generate messages including information associated with the disutility metrics for displaying at requester devices associated with the transportation requests.
1 . A computer-implemented method comprising:
identifying, by a transportation matching system, a shared transportation for a combination of transportation requests comprising at least a first transportation request associated with a first requester device and a second transportation request associated with a second requester device;
determining, by the transportation matching system, estimated service metrics corresponding to subsets of the transportation requests of the shared transportation;
calculating, based on the estimated service metrics, a disutility metric for each transportation request of the transportation requests of the shared transportation; and
providing, for display by the first requester device and based on a calculated disutility metric for the first transportation request, a message associated with the calculated disutility metric for the first transportation request.
2 . The computer-implemented method of claim 1 , wherein:
calculating the disutility metric comprises calculating the disutility metric after completion of the shared transportation; and
providing the message associated with the calculated disutility metric comprises providing the message after completion of the shared transportation.
3 . The computer-implemented method of claim 1 , wherein determining the estimated service metrics corresponding to the subsets of transportation requests comprises determining, for a given subset of the transportation requests, an amount of time associated with traveling to pickup locations and destination locations associated with the subset of the transportation requests.
4 . The computer-implemented method of claim 1 , wherein determining the estimated service metrics corresponding to the subsets of transportation requests comprises determining, for a given subset of the transportation requests a distance associated with traveling to pickup locations and destination locations associated with the given subset of the transportation requests.
5 . The computer-implemented method of claim 1 , wherein calculating the disutility metric for the first transportation request comprises calculating a detour attributable to the first transportation request based on estimated service metrics corresponding to subsets of the transportation requests comprising the first transportation request.
6 . The computer-implemented method of claim 5 , wherein calculating the disutility metric for the first transportation request further comprises calculating the detour attributable to the first transportation request relative to a detour attributable to other transportation requests of the shared transportation, wherein the detour attributable to the first transportation request and the detour attributable to the other transportation requests sum to zero.
7 . The computer-implemented method of claim 1 , further comprising:
generating, using a machine-learning model for predicting disutility metrics and based on the estimated service metrics, a predicted disutility metric for the first transportation request of the shared transportation prior to completion of the shared transportation;
determining a difference between the predicted disutility metric for the first transportation request and the calculated disutility metric for the first transportation request; and
customizing the message based on the difference between the predicted disutility metric and the calculated disutility metric.
8 . A system comprising:
at least one processor; and
at least one non-transitory computer readable storage medium comprising instructions that, when executed by the at least one processor, cause the system to:
identify a shared transportation for a combination of transportation requests comprising at least a first transportation request associated with a first requester device and a second transportation request associated with a second requester device;
determine estimated service metrics corresponding to subsets of the transportation requests of the shared transportation;
calculate, based on the estimated service metrics, a disutility metric for each transportation request of the transportation requests of the shared transportation; and
provide, for display by the first requester device and based on a calculated disutility metric for the first transportation request, a message associated with the calculated disutility metric for the first transportation request.
9 . The system of claim 8 , wherein the instructions that, when executed by the at least one processor, cause the system to:
calculate the disutility metric further cause the system to calculate the disutility metric after completion of the shared transportation; and
provide the message associated with the calculated disutility metric further cause the system to provide the message after completion of the shared transportation.
10 . The system of claim 8 , wherein the instructions that, when executed by the at least one processor, cause the system to determine the estimated service metrics corresponding to the subsets of transportation requests further cause the system to determine, for a given subset of the transportation requests, an amount of time associated with traveling to pickup locations and destination locations associated with the subset of the transportation requests.
11 . The system of claim 8 , wherein the instructions that, when executed by the at least one processor, cause the system to determine the estimated service metrics corresponding to the subsets of transportation requests further cause the system to determine, for a given subset of the transportation requests a distance associated with traveling to pickup locations and destination locations associated with the given subset of the transportation requests.
12 . The system of claim 8 , wherein the instructions that, when executed by the at least one processor, cause the system to calculate the disutility metric for the first transportation request further cause the system to calculate a detour attributable to the first transportation request based on estimated service metrics corresponding to subsets of the transportation requests comprising the first transportation request.
13 . The system of claim 12 , wherein the instructions that, when executed by the at least one processor, cause the system to calculate the disutility metric for the first transportation request further cause the system to calculate the detour attributable to the first transportation request relative to a detour attributable to other transportation requests of the shared transportation, wherein the detour attributable to the first transportation request and the detour attributable to the other transportation requests sum to zero.
14 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to:
generate, using a machine-learning model for predicting disutility metrics and based on the estimated service metrics, a predicted disutility metric for the first transportation request of the shared transportation prior to completion of the shared transportation;
determine a difference between the predicted disutility metric for the first transportation request and the calculated disutility metric for the first transportation request; and
customizing the message based on the difference between the predicted disutility metric and the calculated disutility metric.
15 . A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause a computer system to:
identify a shared transportation for a combination of transportation requests comprising at least a first transportation request associated with a first requester device and a second transportation request associated with a second requester device;
determine estimated service metrics corresponding to subsets of the transportation requests of the shared transportation;
calculate, based on the estimated service metrics, a disutility metric for each transportation request of the transportation requests of the shared transportation; and
provide, for display by the first requester device and based on a calculated disutility metric for the first transportation request, a message associated with the calculated disutility metric for the first transportation request.
16 . The non-transitory computer readable storage medium of claim 15 , wherein the instructions that, when executed by the at least one processor, cause the computer system to:
calculate the disutility metric further cause the computer system to calculate the disutility metric after completion of the shared transportation; and
provide the message associated with the calculated disutility metric further cause the computer system to provide the message after completion of the shared transportation.
17 . The non-transitory computer readable storage medium of claim 15 , wherein the instructions that, when executed by the at least one processor, cause the computer system to determine the estimated service metrics corresponding to the subsets of transportation requests further cause the computer system to determine, for a given subset of the transportation requests, an amount of time associated with traveling to pickup locations and destination locations associated with the subset of the transportation requests.
18 . The non-transitory computer readable storage medium of claim 15 , wherein the instructions that, when executed by the at least one processor, cause the computer system to determine the estimated service metrics corresponding to the subsets of transportation requests further cause the computer system to determine, for a given subset of the transportation requests a distance associated with traveling to pickup locations and destination locations associated with the given subset of the transportation requests.
19 . The non-transitory computer readable storage medium of claim 15 , wherein the instructions that, when executed by the at least one processor, cause the computer system to calculate the disutility metric for the first transportation request further cause the computer system to calculate a detour attributable to the first transportation request based on estimated service metrics corresponding to subsets of the transportation requests comprising the first transportation request.
20 . The non-transitory computer readable storage medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:
generate, using a machine-learning model for predicting disutility metrics and based on the estimated service metrics, a predicted disutility metric for the first transportation request of the shared transportation prior to completion of the shared transportation;
determine a difference between the predicted disutility metric for the first transportation request and the calculated disutility metric for the first transportation request; and
customizing the message based on the difference between the predicted disutility metric and the calculated disutility metric.