Systems and methods for identifying distracted driving events using common features
A distracted driving analysis system for identifying distracted driving events is provided. The system includes a processor in communication with a memory device, and the processor is programmed to: (i) receive labeled training data, the labeled training data including driving event records (a) each labeled as an actual distracted driving event or a passenger event and (b) including phone usage by a user that occurred within a time period of a driving event, (ii) identify common features of the actual distracted driving events and the passenger events by processing the training data using a supervised machine learning algorithm, (iii) generate a trained model based at least in part upon the identified common features, (iv) process a new driving event, (v) assign the new driving event based at least in part upon features of the new driving event, and/or (vi) determine whether the new driving event is an actual distracted driving event or a passenger event.
1. A system for identifying distracted driving events, the system comprising at least one processor, wherein the at least one processor is programmed to:
receive a first plurality of driving records labeled as distracted driving events;
receive a second plurality of driving records labeled as passenger events;
process, using a computational algorithm, the first plurality of driving records to identify one or more first common features, wherein at least one feature of the one or more first common features indicates how a user interacts with a user computing device as a driver;
process, using the computational algorithm, the second plurality of driving records to identify one or more second common features, wherein at least one feature of the one or more second common features indicates how a user interacts with a user computing device as a passenger;
generate a trained machine learning clustering model from an untrained model based at least in part upon the one or more first common features, the one or more second common features, the first plurality of driving records, and the second plurality of driving records by defining coefficients of the trained machine learning clustering model and by determining that a confidence measure associated with clusters generated by the trained machine learning clustering model satisfies a predetermined confidence level;
receive a new driving event associated with a second user; and
determine, using the trained machine learning clustering model, whether the new driving event is a distracted driving event or a passenger event.
2. The system of claim 1 , wherein the at least one processor is further programmed to:
assign a category to the new driving event as an actual distracted driving event or a passenger event; and
assign a confidence level to the category assigned to the new driving event.
3. The system of claim 2 , wherein the at least one processor is further programmed to generate a driver profile for the second user, wherein the driver profile includes the new driving event, as categorized to the category.
4. The system of claim 3 , wherein the at least one processor is further programmed to:
calculate a user safety score based at least in part upon the new driving event, as categorized to the category; and
include the user safety score in the driver profile.
5. The system of claim 4 , wherein the at least one processor is further programmed to generate an insurance policy based at least in part upon the driver profile.
6. The system of claim 1 , wherein the computational algorithm includes at least one of a supervised learning model, an unsupervised learning model, or a reinforcement learning model.
7. The system of claim 1 , wherein the one or more first common features include at least one of average tap rate, tap to swipe ratio, or computing device usage correlated to acceleration events.
8. A computer-implemented method for identifying distracted driving events using a distracted driving analysis system including at least one processor in communication with at least one memory device, the method comprising:
receiving a first plurality of driving records labeled as distracted driving events;
receiving a second plurality of driving records labeled as passenger events;
processing, using a computational algorithm, the first plurality of driving records to identify one or more first common features, wherein at least one feature of the one or more first common features indicates how a user interacts with a user computing device as a driver;
processing, using the computational algorithm, the second plurality of driving records to identify one or more second common features, wherein at least one feature of the one or more second common features indicates how a user interacts with a user computing device as a passenger;
generating a trained machine learning clustering model from an untrained model based at least in part upon the one or more first common features, the one or more second common features, the first plurality of driving records, and the second plurality of driving records by defining coefficients of the trained machine learning clustering model and by determining that a confidence measure associated with clusters generated by the trained machine learning clustering model satisfies a predetermined confidence level;
receiving a new driving event associated with a second user; and
determining, using the trained machine learning clustering model, whether the new driving event is a distracted driving event or a passenger event.
9. The computer-implemented method of claim 8 further comprising:
assigning a category to the new driving event as an actual distracted driving event or a passenger event; and
assigning a confidence level to the category assigned to the new driving event.
10. The computer-implemented method of claim 9 further comprising generating a driver profile for the second user, wherein the driver profile includes the new driving event, as categorized to the category.
11. The computer-implemented method of claim 10 further comprising:
calculating a user safety score based at least in part upon the new driving event, as categorized to the category; and
including the user safety score in the driver profile.
12. The computer-implemented method of claim 11 further comprising generating an insurance policy based at least in part upon the driver profile.
13. The computer-implemented method of claim 8 , wherein the computational algorithm includes at least one of a supervised learning model, an unsupervised learning model, or a reinforcement learning model.
14. The computer-implemented method of claim 8 , wherein the one or more first common features include at least one of selected from a group comprising average tap rate, tap to swipe ratio, or computing device usage correlated to acceleration events.
15. A non-transitory computer-readable storage medium having computer-executable instructions embodied thereon, wherein when executed by a distracted driving analysis system including at least one processor in communication with at least one memory device, the computer-executable instructions cause the at least one processor to:
receive a first plurality of driving records labeled as distracted driving events;
receive a second plurality of driving records labeled as passenger events;
process, using a computational algorithm, the first plurality of driving records to identify one or more first common features, wherein at least one feature of the one or more first common features indicates how a user interacts with a user computing device as a driver;
process, using the computational algorithm, the second plurality of driving records to identify one or more second common features, wherein at least one feature of the one or more second common features indicates how a user interacts with a user computing device as a passenger;
generate a trained machine learning clustering model from an untrained model based at least in part upon the one or more first common features, the one or more second common features, the first plurality of driving records, and the second plurality of driving records by defining coefficients of the trained machine learning clustering model and by determining that a confidence measure associated with clusters generated by the trained machine learning clustering model satisfies a predetermined confidence level;
receive a new driving event associated with a second user; and
determine, using the trained machine learning clustering model, whether the new driving event is a distracted driving event or a passenger event.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the computer-executable instructions further cause the at least one processor to:
assign a category to the new driving event as an actual distracted driving event or a passenger event; and
assign a confidence level to the category assigned to the new driving event.
17. The non-transitory computer-readable storage medium of claim 16 , wherein the computer-executable instructions further cause the at least one processor to generate a driver profile for the second user, wherein the driver profile includes the new driving event, as categorized to the category.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the computer-executable instructions further cause the at least one processor to:
calculate a user safety score based at least in part upon the new driving event, as categorized to the category; and
include the user safety score in the driver profile.
19. The non-transitory computer-readable storage medium of claim 18 , wherein the computer-executable instructions further cause the at least one processor to generate an insurance policy based at least in part upon the driver profile.
20. The non-transitory computer-readable storage medium of claim 15 , wherein the computational algorithm includes at least one of a supervised learning model, an unsupervised learning model, or a reinforcement learning model.
21. A system for identifying distracted driving events, the system comprising:
a means for storing instructions thereon; and
a means for performing operations comprising:
receiving a first plurality of driving records labeled as distracted driving events;
receiving a second plurality of driving records labeled as passenger events;
processing, using a computational algorithm, the first plurality of driving records to identify one or more first common features, wherein at least one feature of the one or more first common features indicates how a user interacts with a user computing device as a driver;
processing, using the computational algorithm, the second plurality of driving records to identify one or more second common features, wherein at least one feature of the one or more second common features indicates how a user interacts with a user computing device as a passenger;
generate a trained machine learning clustering model from an untrained model based at least in part upon the one or more first common features, the one or more second common features, the first plurality of driving records, and the second plurality of driving records by defining coefficients of the trained machine learning clustering model and by determining that a confidence measure associated with clusters generated by the trained machine learning clustering model satisfies a predetermined confidence level;
receiving a new driving event associated with a second user; and
determining, using the trained machine learning clustering model, whether the new driving event is a distracted driving event or a passenger event.