US 12,437,341 B2
Parametric engine to implement methods using parametric analytics
Ryan Michael Gross, Normal, IL (US); M Eric Riley, Sr., Heyworth, IL (US); Jody Ann Thoele, Bloomington, IL (US); Jordan Jeffers, Normal, IL (US); Shawn Renee Harbaugh, Normal, IL (US); Rick Lovings, Normal, IL (US); Joann C. Yant, Bloomington, IL (US); Jenny L. Jacobs, Normal, IL (US); and Erik Skyten, Harriman, TN (US)
Assigned to STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed by STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed on Oct. 10, 2022, as Appl. No. 17/962,816.
Claims priority of provisional application 63/398,750, filed on Aug. 17, 2022.
Prior Publication US 2024/0062306 A1, Feb. 22, 2024
Int. Cl. G06Q 40/08 (2012.01)
CPC G06Q 40/08 (2013.01) 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for performing analysis of parametric events, the computer-implemented method comprising:
receiving, by one or more processors via a distributed ledger, unstructured weather data from a weather oracle network;
measuring, by the one or more processors, an initial water chemical composition for a body of water via one or more water sensors associated with the body of water;
calculating, by the one or more processors and using a first trained machine learning algorithm, a likelihood of a trigger activation for a parametric event for a user based at least upon the unstructured weather data, wherein the calculating includes:
predicting, by the one or more processors, an amount of precipitation for a time period associated with the parametric event based at least upon the unstructured weather data,
predicting, by the one or more processors, a total water chemical composition fluctuation for the body of water based upon the amount of precipitation using the first trained machine learning algorithm, wherein the first trained machine learning algorithm is trained in accordance with historical data indicative of historical chemical composition fluctuation with corresponding historical amounts of precipitation,
calculating, by the one or more processors, a predicted water chemical composition change from the initial water chemical composition for the body of water based upon the total water chemical composition fluctuation, and
calculating, by the one or more processors, the likelihood of the trigger activation, wherein the trigger activation occurs when the predicted water chemical composition change from the initial water chemical composition for the body of water reaches a predetermined threshold proportion of a predetermined chemical;
calculating, by the one or more processors and using a second trained machine learning algorithm, an estimated loss for the user based at least upon the likelihood of the trigger activation;
determining, by the one or more processors, an initial coverage for the user; and
determining, by the one or more processors, whether to offer the user updated coverage for the parametric event based at least upon a comparison of the initial coverage and the estimated loss for the user.