A method for the management of risk selection, the method comprising the steps of:
- inputting an application for insurance for a proposed insured into a node of a computer system, the computer system comprising a plurality of databases of properties of known insureds, the application comprising a plurality of data relating to the proposed insured;
- comparing the plurality of data relating to the proposed insured to a plurality of data comprising risk factors and risk levels;
- determining the risk level for the proposed insured, based upon the inputted application;
- and
- determining whether to offer an insurance policy to the proposed insured, wherein the computer system further comprises:
- a plurality of nodes that are input sources;
- a plurality of insurance company computer systems, the insurance company computer systems being in electronic communication with one or more of the nodes;
- a plurality of broker company computer systems, the broker company computer systems being in electronic communication with one or more of the nodes;
- and
- wherein the plurality of databases further comprises:
- a database comprising information specific to one or more insurance companies;
- a database comprising information specific to one or more businesses other than insurance companies;
- a database comprising a plurality of risk factors and risk classes, the risk classes being determined by a range of amounts previously paid to an insured, the risk classes being defined as low risk, medium risk, and high risk, the low risk class characterized by the lowest range of payments, the high risk class characterized by the highest range of payments made to an insured, and the medium risk class characterized by a range of payments that are between the payments of the low risk class and the high risk class;
- a database comprising a plurality of business characteristics;
- a database comprising a plurality of claims data;
- a database comprising a plurality of insureds data;
- a database comprising a plurality of pricing data;
- a database comprising a plurality of actuarial information;
- a database comprising a plurality of newspaper data;
- a database comprising a plurality of business publications data;
- and
- a database comprising a plurality of public source data,
- wherein the one or more of the databases are stored on a blockchain, and data obtained during the method for the management of risk selection added to the blockchain, enabling the method for the management of risk selection to be completed within a time period ranging from about 1 minute to about 2 hours;
- and
- the method further comprises the step of training the computer system to evaluate risk, including the step of updating one or more of the databases, at periodic intervals, with new risk factors data, new business characteristics data, new claims data, and new insureds data, whereby the computer system is taught to make a decision whether to offer insurance to the proposed insured based on the evaluated risk, without requiring the input of an insurance underwriter;
- and wherein the step of training the computer system to evaluate risk further comprises the steps of:
- providing a plurality of rules for evaluating risk, the rules for evaluating risk including rules for approving insurance, declining insurance, and pending insurance approval, the rules for evaluating risk prepared by an insurance underwriter;
- providing a plurality of insurance company data records;
- and
- providing a plurality of data-driven inferences;
- generating a synthetic dataset for training an Artificial Intelligence (AI) system from the rules for evaluating risk, the insurance company data records, and the data driven inferences;
- using the synthetic dataset being to train the AI system to evaluate risk, creating a trained risk assessment module;
- and
- further training the trained risk assessment module to underwrite insurance, utilizing a second dataset based on review of decisions and input from an insurance underwriter, the second dataset comprising a plurality of actual insurance company records of evaluated risk, the insurance underwriter determining an accuracy rate that the evaluated insurance risk is similar to the second dataset, thereby allowing the computer system to evaluate risk without further review by the insurance underwriter.