| CPC G06Q 40/08 (2013.01) | 20 Claims |
|
8. A computer-implemented method for determining personalized loss event valuations, the method implemented by a computer system including one or more processors, the computer-implemented method comprising:
receiving user data from a user computer device, wherein the user data include data related to personal information and personal property of a user, wherein the user data comprise a user income, a real-estate value associated with the user, and one or more first images of the personal property of the user;
utilizing a trained machine learning model to determine a first loss valuation associated with a first type of loss event based at least in part upon the user data, wherein the trained machine learning model comprises a convolutional neural network, wherein the trained machine learning model is trained, based on features comprising (i) training input data comprising user incomes, real-estate values, and one or more images of damaged property, and (ii) training output data comprising event loss values, using a supervised learning algorithm that identifies functional relationships and maps the training input data to the training output data, to define function coefficients of an untrained model to convert the untrained model to the trained machine learning model, wherein the function coefficients are trained to identify the functional relationships between the training input data and the training output data to enable the trained machine learning model to predict the first loss valuation associated with the first type of loss event based at least in part upon the user data, and wherein the functional relationships comprise identified relationships between the one or more images of damaged property and monetary damages;
generating a loss event policy based at least in part on the first loss valuation;
receiving event data associated with a particular event;
generating a specific event valuation based on the loss event policy and the event data;
receiving third party event data associated with the particular event from a third party computer device, wherein the third party event data comprise at least one of a police report, an emergency services report, a fire services report, fire alarm data, water sensor data, a maintenance report, a home security system report, a smoke detector report, or a power meter report; and
adjusting the specific event valuation to generate a revised event valuation based at least in part upon a specific loss valuation, the specific loss valuation being associated with the personal property affected by the particular event and determined based at least in part on the third party event data, wherein the trained machine learning model is further trained to update the function coefficients based on updated functional relationships between (i) inputs comprising the user data, the event data, and the third party event data, and (ii) an output comprising the revised event valuation.
|