Smart engine risk assessments
View Patent ↗Systems, methods, and computer-readable medium storing instructions can be used to predict insurance information. One of the methods includes obtaining information about an insured entity. The method includes providing the information to a machine learning system, the machine learning system trained to provide insurance information based on the provided information. The method includes in response to providing the information, receiving a prediction of the insurance information. The method also includes adjusting an insurance premium based on the prediction.
1. A computer-implemented method performed by at least one processor, the method comprising:
obtaining first sensor data from one or more first sensors regarding a home of a first insured entity, wherein the first sensor data is indicative of one or more characteristics of the home of the first insured entity;
training a machine learning system comprising a neural network to predict, based on the first sensor data, a total value of claims filed by the first insured entity over a predetermined period such that the predicted total value of claims is within a threshold degree of accuracy, wherein training the machine learning system comprises:
generating a report regarding the first insured entity based on the first sensor data,
extracting a plurality of features from the first report, and
generating a plurality of neurons for the neural network, wherein each of the neurons represents at least one of (i) a characteristic of the first report, or (ii) a relationship between two or more other neurons;
obtaining second sensor data from one or more second sensors regarding a home of a second insured entity;
processing the second sensor data using the trained machine learning system including the plurality of neurons to predict a corresponding total value of claims filed by the second insured entity over the predetermined period; and
adjusting an insurance premium based on the predicted corresponding total value of claims filed by the second insured entity over the predetermined period.
2. The computer-implemented method of claim 1 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from an Internet of Things device of the second insured entity.
3. The computer-implemented method of claim 1 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from financial transactions of the second insured entity.
4. The computer-implemented method of claim 1 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from social media associated with the second insured entity.
5. The computer-implemented method of claim 1 , further comprising providing a recommendation of at least one action that to be taken to alter the predicted corresponding total value of claims filed by the second insured entity over the predetermined period.
6. A system, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor, the memory storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
obtaining first sensor data from one or more first sensors regarding a home of a first insured entity, wherein the first sensor data is indicative of one or more characteristics of the home of the first insured entity;
training a machine learning system comprising a neural network to predict, based on the first sensor data, a total value of claims filed by the first insured entity over a predetermined period such that the predicted total value of claims is within a threshold degree of accuracy, wherein training the machine learning system comprises:
generating a report regarding the first insured entity based on the first sensor data,
extracting a plurality of features from the first report, and
generating a plurality of neurons for the neural network, wherein each of the neurons represents at least one of (i) a characteristic of the first report, or (ii) a relationship between two or more other neurons;
obtaining second sensor data from one or more second sensors regarding a home of a second insured entity;
processing the second sensor data using the trained machine learning system including the plurality of neurons to predict a corresponding total value of claims filed by the second insured entity over the predetermined period; and
adjusting an insurance premium based on the predicted corresponding total value of claims filed by the second insured entity over the predetermined period.
7. The system of claim 6 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from at least one of an Internet of Things device of the second insured entity.
8. The system of claim 6 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from financial transactions of the second insured entity.
9. The system of claim 6 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from social media associated with the second insured entity.
10. The system of claim 6 , wherein the operations further comprise providing a recommendation of at least one action that to be taken to alter the predicted corresponding total value of claims filed by the second insured entity over the predetermined period.
11. A non-transitory computer-readable media storing instructions which, when executed by at least one processor, cause the at least one processor to perform operations comprising:
obtaining first sensor data from one or more first sensors regarding a home of a first insured entity, wherein the first sensor data is indicative of one or more characteristics of the home of the first insured entity;
training a machine learning system comprising a neural network to predict, based on the first sensor data, a total value of claims filed by the first insured entity over a predetermined period such that the predicted total value of claims is within a threshold degree of accuracy, wherein training the machine learning system comprises:
generating a report regarding the first insured entity based on the first sensor data,
extracting a plurality of features from the first report, and
generating a plurality of neurons for the neural network, wherein each of the neurons represents at least one of (i) a characteristic of the first report, or (ii) a relationship between two or more other neurons;
obtaining second sensor data from one or more second sensors regarding a home of a second insured entity;
processing the second sensor data using the trained machine learning system including the plurality of neurons to predict a corresponding total value of claims filed by the second insured entity over the predetermined period; and
adjusting an insurance premium based on the predicted corresponding total value of claims filed by the second insured entity over the predetermined period.
12. The non-transitory computer-readable medium of claim 11 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from at least one of an Internet of Things device of the second insured entity.
13. The non-transitory computer-readable medium of claim 11 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from financial transactions of the second insured entity.
14. The non-transitory computer-readable medium of claim 11 , wherein the total value of claims filed by the second insured entity over the predetermined period is predicted further based on information collected from social media associated with the sensor insured entity.
15. The non-transitory computer-readable medium of claim 11 , wherein the operations further comprise providing a recommendation of at least one action that to be taken to alter the predicted corresponding total value of claims filed by the second insured entity over the predetermined period.
16. The computer-implemented method of claim 1 , wherein the first sensor data comprises at least one of:
a lock state of a door in the home of the first insured entity;
a temperature of water in the home of the first insured entity;
an electricity usage of the home of the first insured entity,
a temperature in the home of the first insured entity, and
a humidity in the home of the first insured entity.