Real Property Monitoring Systems and Methods for Risk Determination
Machine learning techniques for determining a risk level of a target building or other type of real property include receiving data indicative of various historical characteristics of and/or associated with real property, and/or receiving data included in historical, electronic claims pertaining to buildings/real properties, and utilizing the received data to train a machine learning or other model that identifies or discovers risk factors associated with buildings/real properties. The machine learning or other model may be applied to characteristic data associated with the target building/real property to generate risk factors and/or risk indicators of the target building/real property. The techniques may include analyzing the generated risk factors and/or risk indicators to determine a risk level of the target building/real property. The risk factors, risk indicators, and/or risk level may be used for many purposes, such as pricing, quoting, underwriting, or re-underwriting of insurance policies.
1 . A computer-implemented method of determining a risk level of a building or real property, the computer-implemented method comprising, via one or more processors, servers, sensors, and/or transceivers:
training, via the one or more processors and/or servers, a neural network to identify risk factors within a set of historical insurance claims corresponding to buildings and/or real properties, the neural network including a plurality of input layers and one or more output layers, and each input layer of the plurality of input layers including a respective plurality of input parameters, each input parameter of the respective plurality of input parameters corresponding to a respective characteristic of buildings and/or real properties;
receiving, via the one or more processors and/or transceivers, information corresponding to a target building or real property, the received information including respective indications of one or more characteristics of the target building or real property;
analyzing, via the one or more processors and/or servers, the received information using the trained neural network, including generating one or more risk indicators of the target building or real property based upon the received information, the one or more risk indicators including a label indicating a condition of the target building or real property, wherein analyzing the received information comprises:
providing the respective indications of one or more characteristics of the target building or real property to one or more corresponding input layers of the plurality of input layers of the trained neural network; and
generating the label indicating the condition of the target building or real property from an output layer of the one or more output layers using the trained neural network;
determining, via the one or more processors and/or servers, a risk level of the target building or real property based upon the one or more risk indicators; and
providing, via the one or more processors, servers, and/or transceivers, an indication of the risk level of the target building or real property to at least one of a user interface, an application executing on the one or more processors and/or servers, or an application executing on another one or more processors, devices, and/or servers.
2 . The computer-implemented method of claim 1 , wherein:
the neural network is trained based upon at least one of one or more static characteristics or one or more dynamic characteristics of the buildings and/or real properties corresponding to the set of historical insurance claims; and
the received information corresponding to the target building or real property includes respective indications of at least one of one or more static characteristics or one or more dynamic characteristics of the target building or real property.
3 . The computer-implemented method of claim 1 , wherein:
the respective plurality of input parameters of the plurality of input layers of the neural network includes one or more characteristics of applicants and/or insured parties of the set of historical insurance claims;
at least a portion of the received information corresponding to the target building or real property is obtained from an application for or renewal of insurance for the target building or real property; and
the at least the portion of the received information includes respective indications of one or more characteristics of an applicant of the insurance application or renewal.
4 . The computer-implemented method of claim 1 , wherein the computer-implemented method further comprises at least one of: underwriting a new insurance policy for the target building or real property based upon the risk level of the target building or real property, re-underwriting an existing insurance policy of the target building or real property based upon the risk level of the target building or real property, or determining a pricing of the existing insurance policy or of the new insurance policy for the target building or real property based upon the risk level of the target building or real property.
5 . The computer-implemented method of claim 1 , further comprising at least one of dynamically or continuously updating or training the neural network based upon additional insurance claims corresponding to buildings and/or real properties.
6 . A computer system for determining a risk level of a building or real property, the computer system comprising one or more processors, servers, sensors, and/or transceivers configured to:
train a neural network to identify risk factors within a set of historical insurance claims corresponding to buildings and/or real properties, the neural network including a plurality of input layers and one or more output layers, and each input layer of the plurality of input layers includes a respective plurality of input parameters, each input parameter of the respective plurality of input parameters corresponding to a respective characteristic of buildings and/or real properties;
receive wired communication and/or wireless communication or data transmission over one or more radio links or communication channels, the wired communication and/or wireless communication or data transmission including information corresponding to a target building or real property, and the received information including respective indications of one or more characteristics of the target building or real property;
provide the respective indications of one or more characteristics of the target building or real property to one or more corresponding input layers of the plurality of input layers of the trained neural network;
generate a label indicating a condition of the target building or real property from an output layer of the one or more output layers using the trained neural network;
analyze the received information using the trained neural network, including generating one or more risk indicators of the target building or real property based upon the received information, the one or more risk indicators including the label indicating the condition of the target building or real property; and
determine a risk level of the target building or real property based upon the one or more risk indicators.
7 . The computer system of claim 6 , wherein the neural network is trained based upon at least one of one or more static characteristics or one or more dynamic characteristics of the buildings and/or real properties corresponding to the set of historical insurance claims, and wherein the received information corresponding to the target building or real property includes respective indications of at least one of one or more static characteristics or one or more dynamic characteristics of the target building or real property.
8 . The computer system of claim 6 , wherein:
the respective plurality of input parameters of the plurality of input layers of the neural network includes one or more characteristics of applicants and/or insured parties of the set of historical insurance claims;
at least a portion of the received information corresponding to the target building or real property is obtained from an application for or renewal of insurance for the target building or real property; and
the at least the portion of the received information includes respective indications of one or more characteristics of an applicant of the insurance application or renewal.
9 . The computer system of claim 6 , wherein the risk level of the target building or real property is utilized in at least one of: an underwriting of a new insurance policy for the target building or real property, a re-underwriting of an existing insurance policy for the target building or real property, or a determination of one or more terms of the existing insurance policy or of the new insurance policy for the target building or real property.
10 . The computer system of claim 9 , wherein the one or more processors, servers, and/or transceivers are further configured to at least one of underwrite the new insurance policy for the target building or real property, re-underwrite the existing insurance policy for the target building or real property, or determine the one or more terms of the existing insurance policy or of the new insurance policy.
11 . The computer system of claim 6 , wherein the one or more processors, servers, and/or transceivers are further configured to dynamically or continuously update or train the neural network based upon additional insurance claims corresponding to buildings and/or real properties.
12 . A computer-implemented method of determining a risk level of a building or real property, the computer-implemented method comprising, via one or more processors, servers, sensors, and/or transceivers:
training, via the one or more processors and/or servers, a machine learning module or algorithm to identify risk factors within a set of historical insurance claims corresponding to buildings and/or real properties, the machine learning module or algorithm including a plurality of input layers and one or more output layers, and each input layer of the plurality of input layers including a respective plurality of input parameters, each input parameter of the respective plurality of input parameters corresponding to a respective characteristic of buildings and/or real properties;
receiving, via the one or more processors and/or transceivers, information corresponding to a target building or real property, the received information including respective indications of one or more characteristics of the target building or real property;
analyzing, via the one or more processors and/or servers, the received information using the trained machine learning module or algorithm, including generating one or more risk indicators of the target building or real property based upon the received information, the one or more risk indicators including a label indicating a condition of the target building or real property, wherein analyzing the received information comprises:
providing the respective indications of one or more characteristics of the target building or real property to one or more corresponding input layers of the plurality of input layers; and
generating the label indicating the condition of the target building or real property from an output layer of the one or more output layers using the trained machine learning module or algorithm;
determining, via the one or more processors and/or servers, a risk level of the target building or real property based upon the one or more risk indicators; and
providing, via the one or more processors, servers, and/or transceivers, an indication of the risk level of the target building or real property to at least one of a user interface, an application executing on the one or more processors and/or servers, or an application executing on another one or more processors, devices, and/or servers.
13 . The computer-implemented method of claim 12 , wherein the machine learning module or algorithm is trained based upon at least one of one or more static characteristics or one or more dynamic characteristics of the buildings and/or real properties corresponding to the set of historical insurance claims, and wherein the received information corresponding to the target building or real property includes respective indications of at least one of one or more static characteristics or one or more dynamic characteristics of the target building or real property.
14 . The computer-implemented method of claim 12 , wherein:
the respective plurality of input parameters of the plurality of input layers includes one or more characteristics of applicants and/or insured parties of the set of historical insurance claims;
at least a portion of the received information corresponding to the target building or real property is obtained from an application for or renewal of insurance for the target building or real property; and
the at least the portion of the received information includes respective indications of one or more characteristics of an applicant of the insurance application or renewal.
15 . The computer-implemented method of claim 12 , wherein the computer-implemented method further comprises at least one of: underwriting a new insurance policy for the target building or real property based upon the risk level of the target building or real property, re-underwriting an existing insurance policy for the target building or real property based upon the risk level of the target building or real property, or determining a pricing of the new insurance policy or of the existing insurance policy for the target building or real property based upon the risk level of the target building or real property.
16 . The computer-implemented method of claim 12 , further comprising at least one of dynamically or continuously updating or training the machine learning module or algorithm based upon respective additional insurance claims corresponding to buildings and/or real properties.