Using context based machine learning for generation of customized driving outputs

1. A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

train a machine learning model using historical data, wherein training the machine learning model comprises:

classifying the historical data as corresponding to one or more of: a trip context, a device interaction context, a physical condition context, or a personality context corresponding to a driver or passenger, and

training a model corresponding to one or more of the trip context, the device interaction context, the physical condition context, or the personality context, using the corresponding classified historical data;

monitor a data source system to collect new data, wherein the new data includes information from at least a first computing device corresponding to a first driver and a second computing device corresponding to one of: a second driver or a passenger of the first driver or the second driver;

generate, by inputting the new data into the machine learning model, a customized driving output for the first driver, wherein generating of the customized driving output for the first driver is based at least in part on the new data corresponding to the second driver; and

send, to the first computing device, the customized driving output for the first driver and one or more commands directing the first computing device to display the customized driving output for the first driver, wherein sending the one or more commands directing the first computing device to display the customized driving output for the first driver causes the first computing device to display the customized driving output for the first driver.

2. The computing platform of claim 1 , wherein:

a subset of the historical data classified as corresponding to the trip context comprises data indicating one or more of: frequency of difficult driving maneuvers on a route, a number of the difficult driving maneuvers on the route, a type of the difficult driving maneuvers on the route, other drivers' behavior, driving speed, vehicle movement information, vehicle stoppage information, road conditions, road type, type of route, trip duration, time, traffic conditions, weather conditions, or braking information;

the subset of the historical data classified as corresponding to the trip context comprises data corresponding to one or more of: a human driver, a human passenger, or a software agent programmed for autonomous driving; and

the first driver and the second driver comprise one of: a human or a software agent programmed for autonomous driving.

3. The computing platform of claim 2 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

identify that trip context data is not available for the first driver;

identify that trip context data is available for a passenger of a vehicle operated by the first driver;

identify that the first driver and the passenger travel together during a percentage of driving trips that exceeds a predetermined threshold; and

based on identifying that the percentage exceeds the predetermined threshold, use the trip context data for the passenger to train the machine learning model.

4. The computing platform of claim 1 , wherein a subset of the historical data classified as corresponding to the device interaction context comprises data indicating one or more of: a type of device, applications interacted with, actions performed within applications, or frequency of device interactions.

5. The computing platform of claim 1 , wherein a subset of the historical data classified as corresponding to the physical condition context comprises data indicating one or more of: a sleep score, driver disability information, or vital signs of a driver.

6. The computing platform of claim 1 , wherein a subset of the historical data classified as corresponding to the personality context comprises data indicating one or more of: a personality based on driver social media behavior, a personality based on a historical risk score, or personality test result information.

7. The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

store the machine learning model, wherein storing the machine learning model comprises storing a comprehensive model configured to apply one or more of: the trip context model, the device interaction context model, the physical condition context model, or the personality context model.

8. The computing platform of claim 1 , wherein the first driver and the second driver are within a predetermined distance of each other during a driving trip.

9. The computing platform of claim 8 , wherein generating the customized driving output for the first driver comprises generating, based on an identified personality score for the second driver, the customized driving output for the first driver.

10. The computing platform of claim 9 , wherein generating the customized driving output for the first driver comprises generating, in real time, the customized driving output for the first driver.

11. The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

identify, using the machine learning model and based on the customized driving output for the first driver, one or more contextual driving insights indicating a modification to a rate corresponding to the first driver; and

send, to an enterprise computing system, the one or more contextual driving insights and one or more commands directing the enterprise computing system to modify the rate corresponding to the first driver based on the one or more contextual driving insights, wherein sending the one or more commands directing the enterprise computing system to modify the rate corresponding to the first driver based on the one or more contextual driving insights causes the enterprise computing system to modify the rate corresponding to the first driver based on the one or more contextual driving insights.

12. The computing platform of claim 1 , wherein inputting the new data into the machine learning model comprises:

classifying the new data for analysis by one or more of the trip context model, the device interaction context model, the physical condition context model, or the personality context model; and

analyzing the classified new data using the corresponding model.

13. The computing platform of claim 12 , wherein one or more of the trip context model, the device interaction context model, the physical condition context model, or the personality context model are uniquely weighted within the machine learning model to generate the customized driving output.

14. A method comprising:

at a computing platform comprising at least one processor, a communication interface, and memory:

training a machine learning model using historical data, wherein training the machine learning model comprises:

classifying the historical data as corresponding to one or more of: a trip context, a device interaction context, a physical condition context, or a personality context corresponding to a driver or a passenger, and

training a model corresponding to one or more of the trip context, the device interaction context, the physical condition context, or the personality context, using the corresponding classified historical data;

monitoring a data source system to collect new data, wherein the new data includes information from at least a first computing device corresponding to a first driver and a second computing device corresponding to one of: a second driver or a passenger of the first driver or the second driver;

generating, by inputting the new data into the machine learning model, a customized driving output for the first driver, wherein generating of the customized driving output for the first driver is based at least in part on the new data corresponding to the second driver, wherein:

the first driver and the second driver are within a predetermined distance of each other during a driving trip, and

generating the customized driving output for the first driver is based on an identified personality score for the second driver; and

sending, to the first computing device, the customized driving output for the first driver and one or more commands directing the first computing device to display the customized driving output for the first driver, wherein sending the one or more commands directing the first computing device to display the customized driving output for the first driver causes the first computing device to display the customized driving output for the first driver.

15. The method of claim 14 , wherein a subset of the historical data classified as corresponding to the trip context comprises data indicating one or more of: frequency of difficult driving maneuvers on a route, a number of the difficult driving maneuvers on the route, a type of the difficult driving maneuvers on the route, other drivers' behavior, driving speed, vehicle movement information, vehicle stoppage information, road conditions, road type, type of route, trip duration, time, traffic conditions, weather conditions, or braking information.

16. The method of claim 14 , wherein a subset of the historical data classified as corresponding to the device interaction context comprises data indicating one or more of: a type of device, applications interacted with, actions performed within applications, or frequency of device interactions.

17. The method of claim 14 , wherein a subset of the historical data classified as corresponding to the physical condition context comprises data indicating one or more of: a sleep score, driver disability information, or vital signs of a driver.

18. The method of claim 14 , wherein a subset of the historical data classified as corresponding to the personality context comprises data indicating one or more of: a personality based on driver social media behavior, a personality based on a historical risk score, or personality test result information.

19. The method of claim 14 , further comprising:

store the machine learning model, wherein storing the machine learning model comprises storing a comprehensive model configured to apply one or more of the trip context model, the device interaction context model, the physical condition context model, or the personality context model.

20. One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to:

train a machine learning model using historical data, wherein training the machine learning model comprises:

classifying the historical data as corresponding to one or more of: a trip context, a device interaction context, a physical condition context, or a personality context, and

training a model corresponding to one or more of the trip context, the device interaction context, the physical condition context, or the personality context, using the corresponding classified historical data;

monitor a data source system to collect new data, wherein the new data includes information from at least a first computing device corresponding to a first driver and a second computing device corresponding to one of: a second driver or a passenger of the first driver or the second driver;

generate, by inputting the new data into the machine learning model, a customized driving output for the first driver, wherein generating of the customized driving output for the first driver is based at least in part on the new data corresponding to the second driver, wherein:

inputting the new data into the machine learning model comprises:

classifying the new data for analysis by one or more of the trip context model, the device interaction context model, the physical condition context model, or the personality context model, and

analyzing the classified new data using the corresponding model, wherein one or more of the trip context model, the device interaction context model, the physical condition context model, or the personality context model are uniquely weighted within the machine learning model to generate the customized driving output; and

send, to the first computing device, the customized driving output for the first driver and one or more commands directing the first computing device to display the customized driving output for the first driver, wherein sending the one or more commands directing the first computing device to display the customized driving output for the first driver causes the first computing device to display the customized driving output for the first driver.