Systems and methods for creating driving challenges

Abstract

Provided herein is a computer system for creating driving challenges for drivers. The computer system may include a processor in communication with a memory device, and the processor may be programmed to: (i) receive driving data associated with a driver, (ii) generate a first model that models the driving data associated with the driver, (iii) calculate a predicted driving score for the driver based at least in part upon the first model, (iv) generate a second model that predicts a confidence of the predicted driving score, (v) calculate a confidence value of the predicted driving score, wherein the confidence value is a squared error of the predicted driving score, and (vi) generate at least one driving challenge for the driver based at least in part upon the predicted driving score and the confidence value for that predicted driving score.

1 - 20 . (canceled) 
     
     
         21 . A computer system for creating driving challenges for drivers, the computer system comprising at least one processor in communication with at least one memory device, wherein the at least one processor is programmed to:
 receive driving data associated with a driver;   predict a driving score and a confidence value of the predicted driving score for the driver based at least in part upon one or more models including a first model that models the driving data associated with the driver;   generate at least one driving challenge for the driver based at least in part upon the predicted driving score and the confidence value for the predicted driving score;   generate a data distribution based at least in part upon the predicted driving score and the confidence value for the predicted driving score; and   determine a probability that the driver will achieve the predicted driving score based at least in part upon the data distribution.   
     
     
         22 . The computer system of  claim 21 , wherein the first model includes a supervised machine learning model or an unsupervised machine learning model. 
     
     
         23 . The computer system of  claim 21 , wherein the at least one processor is further programmed to:
 generate one or more driving score goals associated with the driver based at least in part upon the probability that the driver will achieve each driving score goal of the one or more driving score goals, wherein the one or more driving score goals includes at least an easy driving score goal that corresponds to a high probability that the driver will achieve the easy driving score goal, a medium driving score goal that corresponds to a moderate probability that the driver will achieve the medium driving score goal, and a low driving score goal that corresponds to a low probability that the driver will achieve the low driving score goal.   
     
     
         24 . The computer system of  claim 23 , wherein the at least one processor is further programmed to:
 generate an actual driving score associated with the driver;   determine whether the actual driving score meets one driving score goal of the one or more driving score goals; and   provide a reward to the driver based at least in part upon the one driving score goal that the driver met, wherein the reward is associated with the probability that the driver would achieve the one driving score goal, and wherein a higher reward is provided based at least in part upon a lower probability that the driver would achieve the one driving score goal.   
     
     
         25 . The computer system of  claim 24 , wherein the driver is insured by an insurance policy with an insurance premium, and wherein the reward includes a discount of the insurance premium or a credit toward the insurance premium. 
     
     
         26 . The computer system of  claim 21 , wherein the at least one processor is further programmed to:
 store the driving data and the first model; and   generate a second model based at least in part upon the first model.   
     
     
         27 . The computer system of  claim 21 , wherein the driving data includes telematics data including braking data, acceleration data, speed data, and demographic data that includes age and location, and wherein the predicted driving score is based at least in part upon at least one selected from a group comprising the braking, acceleration, and speed data. 
     
     
         28 . The computer system of  claim 21 , wherein the at least one processor is further programmed to:
 calculate a mean value of the predicted driving score and a variance of the confidence value; and   generate the data distribution based at least in part upon the calculated mean value and the calculated variance.   
     
     
         29 . A method for creating driving challenges for drivers, the method implemented on one or more processors, the method comprising:
 receiving driving data associated with a driver;   predicting a driving score and a confidence value of the predicted driving score for the driver based at least in part upon one or more models including a first model that models the driving data associated with the driver;   generating at least one driving challenge for the driver based at least in part upon the predicted driving score and the confidence value for the predicted driving score;   generating a data distribution based at least in part upon the predicted driving score and the confidence value for the predicted driving score; and   determining a probability that the driver will achieve the predicted driving score based at least in part upon the data distribution.   
     
     
         30 . The method of  claim 29 , wherein the first model includes a supervised machine learning model or an unsupervised machine learning model. 
     
     
         31 . The method of  claim 29  further comprising:
 generating one or more driving score goals associated with the driver based at least in part upon the probability that the driver will achieve each driving score goal of the one or more driving score goals, wherein the one or more driving score goals includes at least an easy driving score goal that corresponds to a high probability that the driver will achieve the easy driving score goal, a medium driving score goal that corresponds to a moderate probability that the driver will achieve the medium driving score goal, and a low driving score goal that corresponds to a low probability that the driver will achieve the low driving score goal. 
 
     
     
         32 . The method of  claim 31  further comprising:
 generating an actual driving score associated with the driver; 
 determining whether the actual driving score meets one driving score goal of the one or more driving score goals; and 
 providing a reward to the driver based at least in part upon the one driving score goal that the driver met, wherein the reward is associated with the probability that the driver would achieve the one driving score goal, and wherein a higher reward is provided based at least in part upon a lower probability that the driver would achieve the one driving score goal. 
 
     
     
         33 . The method of  claim 32 , wherein the driver is insured by an insurance policy with an insurance premium, and wherein the reward includes a discount of the insurance premium or a credit toward the insurance premium. 
     
     
         34 . The method of  claim 29  further comprising:
 storing the driving data and the first model; and 
 generating a second model based at least in part upon the first model. 
 
     
     
         35 . The method of  claim 29  further comprising:
 calculating a mean value of the predicted driving score and a variance of the confidence value; 
 wherein the generating a data distribution comprises generating the data distribution based at least in part upon the calculated mean value and the calculated variance. 
 
     
     
         36 . One or more non-transitory machine-readable storage media having instructions stored thereon, wherein when executed by one or more processors, the instructions cause the one or more processors to:
 receive driving data associated with a driver;   predict a driving score and a confidence value of the predicted driving score for the driver based at least in part upon one or more models including a first model that models the driving data associated with the driver;   generate at least one driving challenge for the driver based at least in part upon the predicted driving score and the confidence value for the predicted driving score;   generate a data distribution based at least in part upon the predicted driving score and the confidence value for the predicted driving score; and   determine a probability that the driver will achieve the predicted driving score based at least in part upon the data distribution.   
     
     
         37 . The one or more non-transitory machine-readable storage media of  claim 36 , wherein the first model includes a supervised machine learning model or an unsupervised machine learning model. 
     
     
         38 . The one or more non-transitory machine-readable storage media of  claim 36 , wherein the instructions further cause the one or more processors to:
 generate one or more driving score goals associated with the driver based at least in part upon the probability that the driver will achieve each driving score goal of the one or more driving score goals, wherein the one or more driving score goals includes at least an easy driving score goal that corresponds to a high probability that the driver will achieve the easy driving score goal, a medium driving score goal that corresponds to a moderate probability that the driver will achieve the medium driving score goal, and a low driving score goal that corresponds to a low probability that the driver will achieve the low driving score goal.   
     
     
         39 . The one or more non-transitory machine-readable storage media of  claim 38 , wherein the instructions further cause the one or more processors to:
 generate an actual driving score associated with the driver;   determine whether the actual driving score meets one driving score goal of the one or more driving score goals; and   provide a reward to the driver based at least in part upon the one driving score goal that the driver met, wherein the reward is associated with the probability that the driver would achieve the one driving score goal, and wherein a higher reward is provided based at least in part upon a lower probability that the driver would achieve the one driving score goal.   
     
     
         40 . The one or more non-transitory machine-readable storage media of  claim 39 , wherein the driver is insured by an insurance policy with an insurance premium, and wherein the reward includes a discount of the insurance premium or a credit toward the insurance premium. 
     
     
         41 . A system for creating driving challenges for drivers, the system comprising:
 a means for storing instructions thereon;   a means for performing operations comprising:
 receiving driving data associated with a driver; 
 predicting a driving score and a confidence value of the predicted driving score for the driver based at least in part upon one or more models including a first model that models the driving data associated with the driver; 
 generating at least one driving challenge for the driver based at least in part upon the predicted driving score and the confidence value for the predicted driving score; 
 generating a data distribution based at least in part upon the predicted driving score and the confidence value for the predicted driving score; and 
 determining a probability that the driver will achieve the predicted driving score based at least in part upon the data distribution.