Using a predictive request model to optimize provider resources
The present application discloses an improved transportation matching system, and corresponding methods and computer-readable media. According to disclosed embodiments, a transportation matching system trains a predictive request model to generate a metric predicted to trigger an increase in transportation provider activity within the geographic area for a given time period. Furthermore, the system determines a predicted gap between expected request activity and expected transportation provider activity for the geographic area during a future time period, utilizes the predictive request model and the predicted gap to generate a metric for the geographic area, and generates an interactive map associated with a customized schedule for the geographic area and the future time period based on the generated metric.
1. A computer-implemented method comprising:
determining, by a transportation matching system, predicted gaps between predicted requestor times and predicted provider times during future time periods;
generating, by the transportation matching system from the predicted gaps during the future time periods utilizing a predictive request model, provider incentive metrics corresponding to the future time periods, wherein the provider incentive metrics indicate triggering incentives to increase provider device activity to cover the predicted gaps and wherein the predictive request model is trained from training data to generate provider incentive metrics from training gap metrics; and
providing, for display via a provider device, a digital schedule comprising:
a first time element and a first provider incentive metric corresponding to the first time element from the provider incentive metrics, and
a second time element and a second provider incentive metric corresponding to the second time element from the provider incentive metrics.
2. The computer-implemented method of claim 1 , further comprising generating the digital schedule by determining the first time element corresponding to a first predicted gap, the second time element corresponding to a second predicted gap, the first provider incentive metric corresponding to the first predicted gap, and the second provider incentive metric corresponding to the second predicted gap.
3. The computer-implemented method of claim 1 , further comprising providing, for display via an additional provider device, the digital schedule comprising the first time element and the first provider incentive metrics and the second time element and the second provider incentive metric.
4. The computer-implemented method of claim 1 , further comprising generating the digital schedule by generating a customized digital schedule, wherein the provider incentive metrics are customized for the provider device based on historical incentive triggering activity corresponding to the provider device.
5. The computer-implemented method of claim 1 , wherein generating the provider incentive metrics utilizing the predictive request model comprises generating the provider incentive metrics utilizing a machine learning model trained based on historical provider incentive metrics and historical provider responses.
6. The computer-implemented method of claim 1 , further comprising:
generating additional provider incentive metrics during the future time periods from the predicted gaps utilizing the predictive request model for an additional provider device; and
providing, for display via the additional provider device, an additional digital schedule comprising a third time element and a third provider incentive metrics and a fourth time element and a fourth provider incentive metric.
7. The computer-implemented method of claim 1 , wherein generating the provider incentive metrics comprises:
generating the first provider incentive metric for a first geographic area utilizing the predictive request model; and
generating the second provider incentive metric for a second geographic area utilizing the predictive request model.
8. The computer-implemented method of claim 7 , wherein providing the digital schedule comprises providing the first provider incentive metric for the first geographic area and the second provider incentive metric for the second geographic area within the digital schedule.
9. A system comprising:
at least one processor; and
at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the system to:
determine predicted gaps between predicted requestor times and predicted provider times during future time periods;
generate, from the predicted gaps during the future time periods utilizing a predictive request model, provider incentive metrics corresponding to the future time periods, wherein the provider incentive metrics indicate triggering incentives to increase provider device activity to cover the predicted gaps and wherein the predictive request model is trained from training data to generate provider incentive metrics from gap metrics; and
provide, for display via a provider device, a digital schedule comprising:
a first time element and a first provider incentive metric corresponding to the first time element from the provider incentive metrics, and
a second time element and a second provider incentive metric corresponding to the second time element from the provider incentive metrics.
10. The system as recited in claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the digital schedule by determining the first time element corresponding to a first predicted gap, the second time element corresponding to a second predicted gap, the first provider incentive metric corresponding to the first predicted gap, and the second provider incentive metric corresponding to the second predicted gap.
11. The system as recited in claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to provide, for display via an additional provider device, the digital schedule comprising the first time element and the first provider incentive metrics and the second time element and the second provider incentive metric.
12. The system as recited in claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the digital schedule by generating a customized digital schedule, wherein the provider incentive metrics are customized for the provider device based on historical incentive triggering activity corresponding to the provider device.
13. The system as recited in claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the provider incentive metrics utilizing the predictive request model by generating the provider incentive metrics utilizing a machine learning model trained based on historical provider incentive metrics and historical provider responses.
14. The system as recited in claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to:
generate additional provider incentive metrics during the future time periods from the predicted gaps utilizing the predictive request model for an additional provider device; and
provide, for display via the additional provider device, an additional digital schedule comprising a third time element and a third provider incentive metrics and a fourth time element and a fourth provider incentive metric.
15. The system as recited in claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to:
generate the first provider incentive metric for a first geographic area utilizing the predictive request model; and
generate the second provider incentive metric for a second geographic area utilizing the predictive request model; and
provide the digital schedule by providing the first provider incentive metric for the first geographic area and the second provider incentive metric for the second geographic area for display within the digital schedule.
16. A non-transitory computer-readable medium storing instructions thereon that, when executed by at least one processor, cause a computing device to:
determine predicted gaps between predicted requestor times and predicted provider times during future time periods;
generate, from the predicted gaps during the future time periods utilizing a predictive request model, provider incentive metrics corresponding to the future time periods, wherein the provider incentive metrics indicate triggering incentives to increase provider device activity to cover the predicted gaps and wherein the predictive request model is trained from training data to generate provider incentive metrics from training gap metrics; and
provide, for display via a provider device, a digital schedule comprising:
a first time element and a first provider incentive metric corresponding to a first time element from the provider incentive metrics, and
a second time element and a second provider incentive metric corresponding to the second time element from the provider incentive metrics.
17. The non-transitory computer-readable medium of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to generate the digital schedule by determining the first time element corresponding to a first predicted gap, the second time element corresponding to a second predicted gap, the first provider incentive metric corresponding to the first predicted gap, and the second provider incentive metric corresponding to the second predicted gap.
18. The non-transitory computer-readable medium of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to provide, for display via an additional provider device, the digital schedule comprising the first time element and the first provider incentive metrics and the second time element and the second provider incentive metric.
19. The non-transitory computer-readable medium of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to generate the digital schedule by generating a customized digital schedule, wherein the provider incentive metrics are customized for the provider device based on historical incentive triggering activity corresponding to the provider device.
20. The non-transitory computer-readable medium of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to generate the provider incentive metrics utilizing the predictive request model by generating the provider incentive metrics utilizing a machine learning model trained based on historical provider incentive metrics and historical provider responses.