Cognitive blockchain for customized interchange determination

1. A computing system comprising:

a processor configured to detect, via a machine learning model, a change in a creditworthiness attribute of a cardholder has occurred based on patterns in data of the cardholder received from multiple data sources, and dynamically update, via a smart contract of a blockchain, a custom interchange value for the cardholder to be used in payment transactions based on the detected change in the creditworthiness attribute of the cardholder;

a network interface configured to transmit the dynamically updated custom interchange value for the cardholder to a plurality of blockchain peer nodes corresponding to a plurality of different participants of the blockchain; and

a storage configured to store the dynamically determined custom interchange value in a hash-linked chain of blocks of the blockchain,

wherein the processor is further configured to determine that the plurality of blockchain peers have reached a consensus on the dynamically updated custom interchange value prior to storing the dynamically determined custom interchange value.

2. The computing system of claim 1 , wherein the dynamically updated custom interchange value defines a fee to be charged by an entity that covers a cost of credit risk in a payment transaction of the cardholder.

3. The computing system of claim 1 , wherein the machine learning model comprises an unsupervised learning model that identifies relationships between data points from the plurality of data sources.

4. The computing system of claim 1 , wherein the processor is configured to dynamically determine the dynamically updated custom interchange value for the cardholder based on a plurality of attributes included in an enterprise resource planning (ERP) system of an issuer of a payment account of the cardholder.

5. The computing system of claim 1 , wherein the processor is configured to dynamically determine the dynamically updated custom interchange value based on a credit data of other cardholders received from a plurality of blockchain peer nodes.

6. The computing system of claim 1 , wherein the processor is configured to replace a previously assigned custom interchange value of the cardholder with the dynamically updated custom interchange value that comprises a different value.

7. The computing system of claim 1 , wherein the network interface is further configured to receive an authorization request from a merchant point-of-sale (POS) terminal and transmit an authorization response to the merchant POS terminal which comprises the dynamically updated custom interchange value for the cardholder stored in the hash-linked chain of blocks.

8. A method comprising:

detecting, via a machine learning model, a change in a creditworthiness attribute of a cardholder has occurred based on patterns in data of the cardholder received from multiple data source;

dynamically updating, via a smart contract of a blockchain, a custom interchange value for the cardholder to be used in payment transactions based on the detected change in the creditworthiness attribute of the cardholder;

transmitting the dynamically updated custom interchange value for the cardholder to a plurality of blockchain peer nodes corresponding to a plurality of different participants of the blockchain; and

storing the dynamically determined custom interchange value in a hash-linked chain of blocks of the blockchain,

wherein the method further comprises determining that the plurality of blockchain peers have reached a consensus on the dynamically updated custom interchange value prior to storing the dynamically determined custom interchange value.

9. The method of claim 8 , wherein the storing comprises storing the dynamically updated custom interchange value for the cardholder, data hashes and sizes in response to a consensus by a plurality of nodes of the blockchain.

10. The method of claim 8 , wherein the dynamically updated custom interchange value defines a fee to be charged by an entity that covers a cost of credit risk in a payment transaction of the cardholder.

11. The method of claim 8 , wherein the machine learning model comprises an unsupervised learning model that identifies relationships between data points from the plurality of data sources.

12. The method of claim 8 , wherein the dynamically determining comprises dynamically determining the dynamically updated custom interchange value for the cardholder based on a plurality of attributes included in an enterprise resource planning (ERP) system of an issuer of a payment account of the cardholder.

13. The method of claim 8 , wherein the dynamically determining comprises dynamically determining the dynamically updated custom interchange value based on a credit data of other cardholders received from a plurality of blockchain peer nodes.

14. The method of claim 8 , wherein the dynamically updating comprises replacing a previously assigned custom interchange value of the cardholder with the dynamically updated custom interchange value comprising a different value.

15. The method of claim 8 , further comprising receiving an authorization request from a merchant point-of-sale (POS) terminal and transmitting an authorization response to the merchant POS terminal which comprises the dynamically updated custom interchange value for the cardholder stored in the hash-linked chain of blocks.

16. A non-transitory computer readable medium comprising instructions that when read by a processor cause the processor to perform a method comprising:

detecting, via machine learning model, a change in a creditworthiness attribute of a cardholder has occurred based on patterns in data of the cardholder received from multiple data sources;

dynamically updating, via a smart contract of a blockchain, a custom interchange value for the cardholder to be used in payment transactions based on the detected change in the creditworthiness attribute of the cardholder;

transmitting the dynamically updated custom interchange value for the cardholder to a plurality of blockchain peer nodes corresponding to a plurality of different participants of the blockchain; and

storing the dynamically determined custom interchange value in a hash-linked chain of blocks of the blockchain,

wherein the method further comprises determining that the plurality of blockchain peers have reached a consensus on the dynamically updated custom interchange value prior to storing the dynamically determined custom interchange value.

17. The non-transitory computer-readable medium of claim 16 , wherein the dynamically updating comprises dynamically determining the dynamically updated custom interchange value based on a credit data of other cardholders received from a plurality of blockchain peer nodes.

18. The non-transitory computer-readable medium of claim 16 , wherein the dynamically updated custom interchange value defines a fee to be charged by an entity that covers a cost of credit risk in a payment transaction of the cardholder.

19. The non-transitory computer-readable medium of claim 16 , wherein the machine learning model comprises an unsupervised learning model that identifies relationships between data points from the plurality of data sources.