Granted Patent B2

US 12,651,283 · App. 18/989,503 · Granted Jun 9, 2026

Inventors: Benjamin Tarmann (Heyworth, IL); Richard R. Rhodes (Tacoma, WA); Lokesh Awasthy (Santa Clara, CA); Denise DeRoeck (Bloomington, IL); Jaime Skaggs (Chenoa, IL); Jacob J. Alt (Downs, IL); Shanna L. Phillips (Bloomington, IL); Shyam Tummala (Bloomington, IL); Matthew S. Meierotto (Bloomington, IL); Richard D. Groonwald (Bloomington, IL); Brian J. Hughes (Scottsdale, AZ)

Assignee: State Farm Mutual Automobile Insurance Company

G06Q30/0278G06Q40/03G06Q40/03055G06Q40/09G06Q50/16H04L9/0637H04L9/50

Abstract

Claims (50)

1 . A computer-implemented method of using blockchain technology to update information about a customer, the method comprising:

receiving, by a blockchain system, information relating to a customer;

retrieving, by the blockchain system, additional data from a blockchain associated with the customer, wherein the blockchain includes a first block storing the additional data relating to the customer and a second block storing an amount for which the customer is approved for a loan;

executing a machine learning component, based at least in part on the information and the additional data, to determine a risk event associated with the customer;

generating, by the blockchain system and based at least in part on the risk event, a new block including at least one of the additional data or the risk event; and

cryptographically linking, by the blockchain system, the new block to the blockchain.

2 . The computer-implemented method of claim 1 , further comprising:

computing, based at least in part on the risk event, an updated approval amount associated with the customer.

3 . The computer-implemented method of claim 2 , wherein the blockchain comprises:

a third block storing first data representing the risk event; and

a fourth block storing second data representing the updated approval amount.

4 . The computer-implemented method of claim 1 , further comprising:

executing an additional machine learning component, based at least in part on the risk event, configured to predict a likelihood of a delay in a mortgage process associated with the customer.

5 . The computer-implemented method of claim 1 , wherein generating the new block comprises:

determining a hash value based at least in part on a first hash value associated with the information relating to the customer and a second hash value associated with a previous block in the blockchain.

6 . The computer-implemented method of claim 1 , wherein the additional data associated with the customer comprises one or more of a customer age, a marital status, a homeowner status, an income level, income status, an occupation, an insurance status, an education level, an employment status, telematics data, credit score data, deposit account data for down payment, or payment data.

7 . The computer-implemented method of claim 1 , wherein determining the risk event comprises:

receiving, as an output of the machine learning component, a risk value associated with the customer; and

determining that the risk value meets or exceeds a risk threshold.

8 . The computer-implemented method of claim 1 , wherein the machine learning component is trained, using a pool of historical mortgage data, based at least in part on mortgage outcomes and mortgage processing delays across the pool of historical mortgage data.

9 . The computer-implemented method of claim 1 , wherein the blockchain comprises a plurality of permissioned participants, and wherein the method further comprises:

transmitting the new block to a computing device associated with a permissioned participant.

10 . A system for using blockchain technology to update information about a customer, the system comprising:

a processor; and

a non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the processor to perform operations comprising:

receiving information relating to a customer;

retrieving, from a blockchain associated with the customer, additional data relating to the customer, wherein the blockchain includes a first block storing the additional data relating to the customer and a second block storing an amount for which the customer is approved for a loan;

executing a machine learning component, based at least in part on the information relating to a customer and the additional data retrieved from the blockchain, to determine a customer risk profile associated with the customer;

generating a new block based at least in part on the customer risk profile associated with the customer; and

cryptographically linking the new block to the blockchain.

11 . The system of claim 10 , the operations further comprising:

computing, based at least in part on the customer risk profile, an updated approval amount associated with the customer.

12 . The system of claim 10 , the operations further comprising:

executing an additional machine learning component, based at least in part on the customer risk profile, configured to predict a likelihood of a delay in a mortgage process associated with the customer.

13 . The system of claim 10 , wherein the additional data relating to the customer comprises one or more of a customer age, a marital status, a homeowner status, an income level, income status, an occupation, an insurance status, an education level, an employment status, telematics data, credit score data, deposit account data for down payment, or payment data.

14 . The system of claim 10 , wherein the machine learning component is trained, using a pool of historical mortgage data, based at least in part on mortgage outcomes and mortgage processing delays across the pool of historical mortgage data.

15 . The system of claim 10 , wherein the blockchain comprises a plurality of permissioned participants, and wherein the operations further comprise:

transmitting the new block to a computing device associated with a permissioned participant.

16 . One or more non-transitory computer-readable media storing instructions executable by a processor, wherein the instructions, when executed, cause the processor to perform operations comprising:

receiving, by a blockchain system, information relating to a customer;

retrieving, by the blockchain system, a copy of a blockchain associated with a customer, wherein the blockchain includes a first block storing the additional data relating to the customer and a second block storing an amount for which the customer is approved for a loan;

executing a machine learning component, based at least in part on the information and additional data retrieved from the blockchain associated with the customer, to determine a customer risk value associated with the customer;

generating, by the blockchain system and based at least in part on the customer risk value, a new block including at least one of the additional data or the customer risk value associated with the customer; and

cryptographically linking, by the blockchain system, the new block to the blockchain.

17 . The one or more non-transitory computer-readable media of claim 16 , the operations further comprising:

executing a second machine learning component, based at least in part on the customer risk value, configured to predict a likelihood of a delay in a mortgage process associated with the customer.

18 . The one or more non-transitory computer-readable media of claim 16 , wherein the additional data associated with the customer comprises one or more of a customer age, a marital status, a homeowner status, an income level, income status, an occupation, an insurance status, an education level, an employment status, telematics data, credit score data, deposit account data for down payment, or payment data.

19 . The one or more non-transitory computer-readable media of claim 16 , wherein the machine learning component is trained, using a pool of historical mortgage data, based at least in part on mortgage outcomes and mortgage processing delays across the pool of historical mortgage data.

20 . The one or more non-transitory computer-readable media of claim 16 , wherein the blockchain comprises a plurality of permissioned participants, and wherein the operations further comprise:

transmitting the new block to a computing device associated with a permissioned participant.

Continuity (8)

References Cited (186)