Transportation route error detection and adjustment
Methods and systems for correcting errors in transportation routes are provided. In one embodiment, a method is provided that includes receiving a transportation request that includes at least two locations. A first route prediction may be generated based on a first set of previously-completed routes associated with the at least two locations. A first predictive model may compare the first route prediction with route information associated with a second set of previously-completed routes identified based on the first route prediction. A second route prediction may be generated based on the comparison and may be sent to a mobile device for presentation to a user.
1. A computer-implemented method comprising:
receiving, by a transportation matching system, a transportation request from a mobile device, wherein the transportation request comprises at least two locations;
generating, in response to the transportation request, an initial route prediction, wherein the initial route prediction is generated utilizing a first predictive model based on a first set of previously-completed routes associated with the at least two locations;
comparing, utilizing a second predictive model, the initial route prediction generated utilizing the first predictive model with route information associated with a second set of previously-completed routes identified at least in part based on the initial route prediction;
generating, based on the comparison, a corrected route prediction for the transportation request; and
training the second predictive model by:
receiving, after fulfillment of the transportation request, actual route information corresponding to the fulfillment of the transportation request;
determining one or more errors between the corrected route prediction and the actual route information; and
updating the second predictive model based on the one or more errors.
2. The computer-implemented method of claim 1 , further comprising identifying the second set of previously-completed routes utilizing one or more weights of the second predictive model.
3. The computer-implemented method of claim 2 , wherein training the second predictive model comprises updating the one or more weights of the second predictive model used to identify the second set of previously-completed routes.
4. The computer-implemented method of claim 1 , further comprising:
identifying, based on the comparison, at least one route prediction error in the initial route prediction; and
training the first predictive model based on the at least one route prediction error.
5. The computer-implemented method of claim 4 , wherein the at least one route prediction error comprises at least one error selected from a group comprising:
a pickup time error for a vehicle assigned to service the transportation request,
a pickup distance error for a vehicle assigned to service the transportation request,
a travel time error for an amount of time spent in transit between the at least two locations, and
a distance error for a total amount of distance traveled between the at least two locations.
6. The computer-implemented method of claim 4 , wherein training the first predictive model comprises updating one or more weights of the first predictive model used to identify the first set of previously-completed routes.
7. A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause the at least one processor to:
receiving, by a transportation matching system, a transportation request from a mobile device, wherein the transportation request comprises at least two locations;
generating, in response to the transportation request, an initial route prediction, wherein the initial route prediction is generated utilizing a first predictive model based on a first set of previously-completed routes associated with the at least two locations;
comparing, utilizing a second predictive model, the initial route prediction generated utilizing the first predictive model with route information associated with a second set of previously-completed routes identified at least in part based on the initial route prediction;
generating, based on the comparison, a corrected route prediction for the transportation request; and
training the second predictive model by:
receiving, after fulfillment of the transportation request, actual route information corresponding to the fulfillment of the transportation request;
determining one or more errors between the corrected route prediction and the actual route information; and
updating the second predictive model based on the one or more errors.
8. The non-transitory computer readable storage medium of claim 7 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to identify the second set of previously-completed routes utilizing one or more weights of the second predictive model.
9. The non-transitory computer readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to train the second predictive model by updating the one or more weights of the second predictive model used to identify the second set of previously-completed routes.
10. The non-transitory computer readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to:
identify, based on the comparison, at least one route prediction error in the initial route prediction; and
train the first predictive model based on the at least one route prediction error.
11. The non-transitory computer readable storage medium of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to select the at least one route prediction error from:
a pickup time error for a vehicle assigned to service the transportation request,
a pickup distance error for a vehicle assigned to service the transportation request,
a travel time error for an amount of time spent in transit between the at least two locations, or
a distance error for a total amount of distance traveled between the at least two locations.
12. The non-transitory computer readable storage medium of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to update one or more weights of the first predictive model used to identify the first set of previously-completed routes.
13. The non-transitory computer readable storage medium of claim 7 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to identify the second set of previously-completed routes based on a similarity with the initial route prediction selected, the similarity comprising at least one a similar predicted starting location, a similar predicted ending location, a similar predicted travel distance, a similar predicted travel time, or a similar predicted route.
14. A system comprising:
at least one processor; and
a non-transitory computer-readable medium comprising instructions that, when executed by the at least one processor, to cause the system to:
receive, by a transportation matching system, a transportation request from a mobile device, wherein the transportation request comprises at least two locations;
generate, in response to the transportation request, an initial route prediction, wherein the initial route prediction is generated utilizing a first predictive model based on a first set of previously-completed routes associated with the at least two locations;
compare, utilizing a second predictive model, the initial route prediction generated utilizing the first predictive model with route information associated with a second set of previously-completed routes identified at least in part based on the initial route prediction;
generate, based on the comparison, a corrected route prediction for the transportation request; and
train the second predictive model by:
receiving, after fulfillment of the transportation request, actual route information corresponding to the fulfillment of the transportation request;
determining one or more errors between the corrected route prediction and the actual route information; and
updating the second predictive model based on the one or more errors.
15. The system of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the system to identify the second set of previously-completed routes utilizing one or more weights of the second predictive model.
16. The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to train the second predictive model by updating the one or more weights of the second predictive model used to identify the second set of previously-completed routes.
17. The system of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the system to:
identify, based on the comparison, at least one route prediction error in the initial route prediction; and
train the first predictive model based on the at least one route prediction error.
18. The system of claim 17 , further comprising instructions that, when executed by the at least one processor, cause the system to select the at least one route prediction error from:
a pickup time error for a vehicle assigned to service the transportation request,
a pickup distance error for a vehicle assigned to service the transportation request,
a travel time error for an amount of time spent in transit between the at least two locations, or
a distance error for a total amount of distance traveled between the at least two locations.
19. The system of claim 17 , further comprising instructions that, when executed by the at least one processor, cause the system to train the first predictive model by updating one or more weights of the first predictive model used to identify the first set of previously-completed routes.
20. The system of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the corrected route prediction by generating one or more of a corrected pickup time for a vehicle assigned to service the transportation request, a corrected drop-off time associated with the transportation request, or a corrected travel time associated with the transportation request.