Intelligently customizing a cancellation notice for cancellation of a transportation request based on transportation features
The present disclosure relates to systems, non-transitory computer-readable media, and methods for intelligently determining to assess (or not assess) a cancellation penalty and notifying a requestor device of such a penalty in response to either a requestor's selection to cancel a single transportation request for a requestor or a requestor's selection to cancel a shared-transportation request associated with multiple requestors. For example, the disclosed systems can generate conversion probabilities for a requestor reflecting if a cancellation penalty is assessed—and if the cancellation penalty is not assessed—for a cancellation of a transportation request for transport of a lone requestor. Based on the conversion probabilities, the disclosed systems customize a cancellation notice for a requestor device to either include or exclude the cancellation penalty.
1 . A computer-implemented method comprising:
training a requestor-feedback-machine-learning model utilizing ground-truth requestor device feedback interactions and historical transportation features comprising historical cancellation transmissions;
receiving a transportation request corresponding to a transportation matching system from a requestor device;
receiving, from the requestor device, an indication of a selection to cancel the transportation request;
extracting a set of transportation features corresponding to the transportation request;
generating, from the set of transportation features utilizing the requestor-feedback-machine-learning model, a first requestor device feedback probability that the requestor device will transmit a feedback notification if a cancellation penalty notification comprising a first cancellation penalty amount for cancelling the transportation request is transmitted to the requestor device;
generating, from the set of transportation features utilizing the requestor-feedback-machine-learning model, a second requestor device feedback probability that the requestor device will transmit a feedback notification if a cancellation penalty notification comprising a second cancellation penalty amount for cancelling the transportation request is transmitted to the requestor device; and
based on a comparison of the first requestor device feedback probability and the second requestor device feedback probability, in response to receiving the indication of the selection to cancel the transportation request from the requestor device, providing a customized cancellation notice comprising the first cancellation penalty amount for display on the requestor device.
2 . The computer-implemented method of claim 1 , wherein training the requestor-feedback-machine-learning model comprises:
generating, utilizing the requestor-feedback-machine-learning model, a requestor device feedback prediction; and
comparing the requestor device feedback prediction with a ground truth requestor device feedback.
3 . The computer-implemented method of claim 2 , wherein training the requestor-feedback-machine-learning model comprises:
comparing the requestor device feedback prediction with a ground truth requestor device feedback utilizing a loss function to determine a loss; and
modifying parameters of the requestor-feedback-machine-learning model based on the loss.
4 . The computer-implemented method of claim 1 wherein extracting the set of transportation features corresponding to the transportation request comprises extracting at least one of:
a number of communications exchanged with the requestor device; or
an amount of time for matching the transportation request with a provider device.
5 . The computer-implemented method of claim 1 wherein extracting the set of transportation features corresponding to the transportation request comprises extracting at least one of:
an estimated time of arrival of a provider device at a pickup location of the requestor device;
an amount of requestor device movement after sending the transportation request; or
a predicted amount of detour corresponding to the transportation request.
6 . The computer-implemented method of claim 1 , further comprising generating, from the set of transportation features utilizing a requestor-experiment-rating-machine-learning model a predicted requestor rating if a cancellation penalty notification for cancelling the transportation request is transmitted to the requestor device.
7 . The computer-implemented method of claim 6 , further comprising providing the customized cancellation notice based on the first requestor device feedback probability and the predicted requestor rating.
8 . The computer-implemented method of claim 1 , wherein providing the customized cancellation notice comprises:
providing a first digital notification to the requestor device of a cancellation penalty associated with cancelling the transportation request; or
providing a second digital notification to the requestor device that no cancellation penalty will be assessed for cancelling the transportation request.
9 . A system comprising:
at least one processor; and
at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, causes the system to:
train a requestor-feedback-machine-learning model utilizing ground-truth requestor device feedback interactions and historical transportation features comprising historical cancellation transmissions;
receive a transportation request corresponding to a transportation matching system from a requestor device;
receive, from the requestor device, an indication of a selection to cancel the transportation request;
extract a set of transportation features corresponding to the transportation request;
generate, from the set of transportation features utilizing the requestor-feedback-machine-learning model, a first requestor device feedback probability that the requestor device will transmit a feedback notification if a cancellation penalty notification comprising a first cancellation penalty amount for cancelling the transportation request is transmitted to the requestor device;
generate, from the set of transportation features utilizing the requestor-feedback-machine-learning model, a second requestor device feedback probability that the requestor device will transmit a feedback notification if a cancellation penalty notification comprising a second cancellation penalty amount for cancelling the transportation request is transmitted to the requestor device; and
based on a comparison of the first requestor device feedback probability and the second requestor device feedback probability, in response to receiving the indication of the selection to cancel the transportation request from the requestor device, provide a customized cancellation notice comprising the first cancellation penalty amount for display on the requestor device.
10 . The system of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to train the requestor-feedback-machine-learning model by:
generating, utilizing the requestor-feedback-machine-learning model, a requestor device feedback prediction;
comparing the requestor device feedback prediction with a ground truth requestor device feedback to determine a loss; and
modifying parameters of the requestor-feedback-machine-learning model based on the loss.
11 . The system of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to extract the set of transportation features corresponding to the transportation request by extracting at least one of:
a number of communications exchanged with the requestor device; or
an amount of time for matching the transportation request with a provider device.
12 . The system of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to extract the set of transportation features corresponding to the transportation request by extracting at least one of:
an estimated time of arrival of a provider device at a pickup location of the requestor device;
an amount of requestor device movement after sending the transportation request; or
a predicted amount of detour corresponding to the transportation request.
13 . The system of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to generate, from the set of transportation features, utilizing a requestor-experiment-rating-machine-learning model, a predicted requestor rating if a cancellation penalty notification for cancelling the transportation request is transmitted to the requestor device.
14 . The system of claim 13 , further comprising instructions that, when executed by the at least one processor, cause the system to provide the customized cancellation notice based on the first requestor device feedback probability and the predicted requestor rating.
15 . A non-transitory computer-readable medium comprising instructions that, when executed by at least one processor, causes a computer system to:
train a requestor-feedback-machine-learning model utilizing ground-truth requestor device feedback interactions and historical transportation features comprising historical cancellation transmissions;
receive a transportation request corresponding to a transportation matching system from a requestor device;
receive, from the requestor device, an indication of a selection to cancel the transportation request;
extract a set of transportation features corresponding to the transportation request;
generate, from the set of transportation features utilizing the requestor-feedback-machine-learning model, a first requestor device feedback probability that the requestor device will transmit a feedback notification if a cancellation penalty notification comprising a first cancellation penalty amount for cancelling the transportation request is transmitted to the requestor device;
generate, from the set of transportation features utilizing the requestor-feedback-machine-learning model, a second requestor device feedback probability that the requestor device will transmit a feedback notification if a cancellation penalty notification comprising a second cancellation penalty amount for cancelling the transportation request is transmitted to the requestor device; and
based on a comparison of the first requestor device feedback probability and the second requestor device feedback probability, in response to receiving the indication of the selection to cancel the transportation request from the requestor device, provide a customized cancellation notice comprising the first cancellation penalty amount for display on the requestor device.
16 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to train the requestor-feedback-machine-learning model by:
generating, utilizing the requestor-feedback-machine-learning model, a requestor device feedback prediction;
comparing the requestor device feedback prediction with a ground truth requestor device feedback to determine a loss; and
modifying parameters of the requestor-feedback-machine-learning model based on the loss.
17 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to extract the set of transportation features corresponding to the transportation request by extracting at least one of:
a number of communications exchanged with the requestor device; or
an amount of time for matching the transportation request with a provider device.
18 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to extract the set of transportation features corresponding to the transportation request by extracting at least one of:
an estimated time of arrival of a provider device at a pickup location of the requestor device;
an amount of requestor device movement after sending the transportation request; or
a predicted amount of detour corresponding to the transportation request.
19 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to: generate, from the set of transportation features, utilizing a requestor-experiment-rating-machine-learning model, a predicted requestor rating if a cancellation penalty notification for cancelling the transportation request is transmitted to the requestor device.
20 . The non-transitory computer-readable medium of claim 19 , further comprising instructions that, when executed by the at least one processor, cause the computer system to provide the customized cancellation notice based on the first requestor device feedback probability and the predicted requestor rating.