Abstract: 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.

Abstract: Systems and methods for providing continuous safe-driver training safely are provided. A safe-driving challenge may be presented to an operator of a vehicle. Data captured by sensors associated with the vehicle may be analyzed to determine whether the operator of the vehicle has completed the safe-driving challenge. Based on a determination that the operator of the vehicle has completed the safe-driving challenge, a notification may be provided to the operator (e.g., indicating to the operator that he or she has successfully completed the challenge). A processor may randomly select whether a reward is to be provided to the operator of the vehicle based on the determination that the operator of the vehicle has completed the safe-driving challenge. Moreover, if a reward is to be provided to the operator of the vehicle, a processor may randomly select a type of reward to be provided to the operator of the vehicle.

Abstract: A system for one-click two-factor includes a processor and a non-transitory, tangible, computer-readable storage medium having instructions stored thereon that, in response to execution by the processor, cause the processor to perform operations including: (i) receiving an access request from a user, the access request including a first authentication factor; (ii) generating a second authentication factor and a hyperlink that includes the second authentication factor; (iii) providing the hyperlink that includes the second authentication factor to a client device associated with the user; (iv) automatically receiving the second authentication factor in response to selection of the hyperlink by the user; and (v) verifying the first authentication factor and the second authentication factor to authenticate the identity of the user.

Abstract: A system for displaying information indicative of driving conditions, to a driver, using a smart ring are disclosed. An exemplary system includes a smart ring with a ring band having a plurality of surfaces including an inner surface, an outer surface, a first side surface, and a second side surface. The system further includes a processor, configured to obtain data from a communication module within the ring band, or from one or more sensors disposed within the ring band. The obtained data are representative of information indicative of one or more driving conditions to be displayed to the driver. The smart ring also includes a projector module display disposed on at least one of the plurality of surfaces, and configured to present information indicative of the one or more driving conditions.

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.

Abstract: A computer-implemented method for improving compression of predictive models includes generating an unlabeled simulated data set by expanding an initial data set, and generating a labeled data set by predicting the unlabeled, simulated data set using a complex model to output a plurality of labels. The method also includes training a relatively simple neural network using the labeled data set.

Abstract: Systems and methods for generating calm or quiet routes are provided. When a user requests navigation directions and indicates a preference for a calm route, a plurality of routes between the origin location and the destination location requested by the user may be identified. Historical sensor data (e.g., including heart rate data, exterior vehicle noise level data, accelerometer data) and traffic data associated with route segments of each of the routes may be analyzed to identify indications of calmness associated with each route segment. Current traffic data associated with the route segments may be analyzed to assign a traffic score representing a level of congestion along the segment and corresponding to a level of insurance risk associated with traversing the segment. Based at least in part upon the indications of calmness and the traffic score associated with each route segment, a route may be selected and presented to the user.

Abstract: A system for displaying contextually-sensitive braking information on a surface of a vehicle is presented. The system may include a transceiver, one or more memories, an electronic display disposed on the surface, and one or more processors. The one or more processors may be configured to detect a braking event of the vehicle, wherein the braking event has an associated braking force. The one or more processors may compare the braking force to a predetermined threshold braking force to determine whether the braking force exceeds the threshold braking force. The one or more processors may further cause the electronic display to display a braking indication having an intensity that is proportional to the braking force, wherein the braking indication may include a braking rationale corresponding to the braking event in response to determining that the braking force exceeds the threshold braking force.

Abstract: A distracted driving analysis system for identifying distracted driving events is provided. The system includes a processor in communication with a memory device programmed to: (i) receive driving event records including phone usage by a user that occurred within a time period of a driving event, (ii) divide the driving event records into at least two clusters based at least in part upon common features of one or more driving event records of the plurality of driving event records by processing the driving event records using an unsupervised machine learning algorithm, (iii) generate a trained model based at least in part upon the at least two clusters including cluster labels, (iv) process a new driving event using the trained model, (v) assign the new driving event to one of the at least two clusters using the trained model, and (vi) based at least in part upon the cluster labels for the assigned cluster, determine whether the new driving event is an actual distracted driving event or a passenger event.

Abstract: A video analytics based image verification system for obtaining initial vehicle profiles is presented. The system may include an external processing server that receives a location of a vehicle and proximate traffic information to determine whether it is safe for a user to obtain an initial vehicle profile. The external processing server may further determine first and second profile features from video data indicative of the vehicle. The external processing server may compare the second profile feature to an image verification indicator to generate an image verification score. A provider server may receive the first profile feature and the image verification score from the external processing server, and update a risk evaluation to include the initial vehicle profile if the image verification score is above an image verification threshold.

Abstract: Systems and methods of automatically controlling a user's data footprint are provided. Data associated with a user may be analyzed to determine an action the user is preparing to take. Based on the analysis, a potential risk associated with the action the user is preparing to take may be identified. The potential risk associated with the action the user is preparing to take may be, for example, a data security risk, a data privacy risk, a physical risk, a risk of damage to property, and/or a financial risk. A notification indicating the potential risk associated with the action the user is preparing to take may be provided to the user. The notification may include one or more suggestions for mitigating the potential risk associated with the action the user is preparing to take.

Abstract: Method and system for verifying a reliability of sensor data received from a mobile device of a user are disclosed. For example, the method includes receiving first sensor data collected and/or generated by one or more sensors of the mobile device from an application installed on a mobile device of a user at a first time, receiving second sensor data collected and/or generated by the one or more sensors of the mobile device from the application at a second time, determining whether the mobile device is in a vehicle that the user is driving during a time interval based at least upon the first sensor data and the second sensor data, and in response to the mobile device not being in the vehicle that the user is driving during the time interval, transmitting a notification to the mobile device indicating that the application does not work properly.

Abstract: Systems and methods for analyzing documentation for assessing potential fraudulent user submissions are provided. According to certain aspects, a server computer may receive an initial set of documentation descriptive of damage to a property asset, and may analyze the initial set of documentation to determine whether additional documentation is needed. The server computer may initiate a communication channel with a user device via which the additional documentation may be submitted, and the server computer may similarly analyze the additional documentation to determine a likelihood of fraud. The server computer may process the user submission accordingly.

Abstract: Method and system for determining a status of a mobile device of a user are disclosed. For example, the method includes receiving first sensor data at a first time from an application installed on a mobile device of a user, determining a first location of the mobile device, immediately subsequent to receiving the first sensor data at the first time, receiving second sensor data at a second time from the application, the second time following the first time by a time interval, determining a second location of the mobile device, determining a distance between the first location and the second location, determining whether the distance corresponding to the time interval exceeds a predetermined threshold, and determining whether a trip log indicative of at least one trip during the time interval is received from the application.

Abstract: Method and system for granting in-game resources for a telematics-based game.

Abstract: A system and method for analyzing risk and providing risk mitigation instructions. The system receives analyzes sensor data and other data corresponding to a user to determine a test group. The system uses the test group to determine a risk score, and, subsequently, a risk mitigation strategy. Machine learning techniques are implemented to refine how the test group, risk score, and mitigation are each selected.

Abstract: Method and system for presenting in-game objectives in a virtual game. For example, the method includes determining first real-world driving characteristics based upon first real-world telematics data of a first real-world user, determining second real-world driving characteristics based upon second real-world telematics data of a second real-world user, generating a shared virtual map based upon the first real-world driving characteristics and the second real-world driving characteristics, generating a shared in-game objective based upon the shared virtual map, presenting the shared in-game objective to a first virtual character associated with the first real-world driving characteristics of the first real-world user and a second virtual character associated with the second real-world driving characteristics of the second real-world user, and allowing the first virtual character and the second virtual character to accomplish the shared in-game objective in the shared virtual map.

Abstract: A user computing device for identifying a driver of a vehicle on a trip is provided. The user computing device is associated with a first vehicle occupant, and is programmed to: (i) detect a second user computing device associated with a second vehicle occupant, (ii) initiate a ping exchange process including emitting a set of non-audible sonic ping signals and detecting a set of signals from the second user computing device over a duration of the trip, (iii) generate a relative positioning map of the user computing device with respect to the second user computing device, (iv) determine that the first vehicle occupant is one of a driver and a passenger of the vehicle, and (v) transmit, to a driver identification (“DI”) server, a trip report including the determination and the generated relative positioning map.

Abstract: Method and system for training a virtual character of a telematics-based game. In some examples, a computer-implemented method includes: determining, based at least in part upon telematics data, a plurality of skill points associated with a plurality of real skills exhibited by the user during the one or more real trips; training a virtual character by at least updating, based at least in part upon the plurality of skill points, the plurality of virtual ratings; generating, based at least in part upon the character profile, one or more virtual occurrences to be encountered by the virtual character; determining, based at least in part upon the updated plurality of virtual ratings, one or more outcomes associated with the one or more virtual occurrences; updating the character profile by at least applying the one or more virtual occurrences based on the associated one or more outcomes to the virtual character.

Abstract: A machine learning model is manufactured by a process including retrieving training data, minimizing a loss function, wherein the training data may include labeled or unlabeled data, the machine learning model generating a prediction. A machine learning training/operation server includes a processor and a memory storing instructions that, when executed by the processor, cause the server to retrieve training data, input a training input, analyze the training input to generate a prediction, generate a loss score, and store the trained machine learning model. A method for training a machine learning model includes receiving training data, inputting a training input, analyzing the training input, generating a loss score, and storing the trained machine learning model.