System and method for unsupervised abstraction of sensitive data for detection model sharing across entities

1. A computer-implemented method for generating a standard customer profile in a data processing system comprising a processing device and a memory comprising instructions which are executed by the processing device, the method comprising:

receiving customer data from a plurality of computing devices over a network, the customer data including information for a plurality of customers to a plurality of entities;

performing, by the processing device, unsupervised learning on the customer data to produce a plurality of clusters of customers with a plurality of features in common;

determining, by the processing device, that a cluster represents a standard customer and storing a plurality of standard customer profiles based on the determined standard customers, wherein each of the plurality of standard customer profiles comprise a cluster and randomly selected identifying information;

generating a plurality of artificial customer profiles by combining randomly selected information from real customer profile data;

providing the plurality of artificial customer profiles to a cognitive system for generating synthetic transaction data based on the standard customer through a reinforcement learning model, wherein generating synthetic transaction data comprises:

providing standard customer transaction data representing a group of real customers having similar transaction data as a goal;

simulating a plurality of transactions via an action;

comparing the plurality of transactions with the goal;

providing feedback associated with the action based on a degree of similarity relative to the goal;

adjusting a policy based on the feedback;

repeating the simulating and adjusting of the policy until a degree of similarity between the plurality of transactions and the goal is higher than a predefined threshold; and

outputting the resulting plurality of transactions as the synthetic transaction data;

combining one of the plurality of artificial customer profiles with the simulated transaction data to form simulated customer data;

training, by the processing device, a detection model for detecting activity based on the simulated customer data; and

distributing the detection model to computing devices over the network.

2. The method of claim 1 , wherein the information for the plurality of customers comprises identifying information and transaction information, wherein the identifying information comprises a name, contact information, and finance information, and wherein finance information comprises one of a credit score, a wage, and a revenue.

3. The method of claim 1 , further comprising filtering the customer data prior to performing unsupervised learning.

4. The method of claim 3 , wherein the filtering comprises a recency, frequency, monetary value analysis to group customers.

5. The method of claim 1 , wherein each of the plurality of standard customer profiles comprise a plurality of data distributions for the plurality of features in common.

6. The method of claim 1 , further comprising determining that a sub-cluster represents a standard customer by applying one or more rules.

7. The method of claim 6 , wherein the one or more rules comprise a size determination indicating a minimum or maximum number of customers in a sub-cluster that is determined to be a standard customer.

8. The method of claim 1 , wherein the real customer profile data includes address, first name, second name, phone number, email address, credit score, and wage.

9. An abstraction system comprising a processing device and a memory comprising instructions which are executed by the processing device for generating a standard customer profile in a data processing system configured to:

receive customer data from a plurality of computing devices over a network, the customer data including information for a plurality of customers to a plurality of entities;

perform, by the processing device, unsupervised learning on the customer data to produce a plurality of clusters of customers with a plurality of features in common;

determine, by the processing device, that a cluster represents a standard customer and storing a plurality of standard customer profiles based on the determined standard customers, wherein each of the plurality of standard customer profiles comprise a cluster and randomly selected identifying information;

generate a plurality of artificial customer profiles by combining randomly selected information from real customer profile data;

provide the plurality of artificial customer profiles to a cognitive system for generating synthetic transaction data based on the standard customer through a reinforcement learning model, wherein generating synthetic transaction data comprises:

providing standard customer transaction data representing a group of real customers having similar transaction data as a goal;

simulating a plurality of transactions via an action;

comparing the plurality of transactions with the goal;

providing feedback associated with the action based on a degree of similarity relative to the goal;

adjusting a policy based on the feedback;

repeating the simulating and adjusting of the policy until a degree of similarity between the plurality of transactions and the goal is higher than a predefined threshold; and

outputting the resulting plurality of transactions as the synthetic transaction data;

combine one of the plurality of artificial customer profiles with the simulated transaction data to form simulated customer data;

train, by the processing device, a detection model for detecting activity based on the simulated customer data; and

distribute the detection model to each of the computing devices over the network.

10. The abstraction system of claim 9 , wherein the information for the plurality of customers comprises identifying information and transaction information, wherein the identifying information comprises a name, contact information, and finance information, and wherein finance information comprises one of a score, a wage, and a revenue.

11. The abstraction system of claim 9 , wherein the processing device is further configured to filter the customer data prior to performing unsupervised learning.

12. The abstraction system of claim 11 , wherein the filtering comprises a recency, frequency, monetary value analysis to group customers.

13. The abstraction system of claim 9 , wherein the standard customer profiles comprise a plurality of data distributions for the plurality of features in common.

14. The abstraction system of claim 9 , further comprising determining that a sub-cluster represents a standard customer by applying one or more rules.

15. The abstraction system of claim 14 , wherein the one or more rules comprise a size determination indicating a minimum or maximum number of customers in a sub-cluster that is determined to be a standard customer.

16. A computer program product comprising a non-transitory computer readable medium having stored thereon instructions that when executed by a processor performs a method comprising:

receiving customer data from a plurality of computing devices over a network, the customer data including information for a plurality of customers to a plurality of entities;

performing, by the processor, unsupervised learning on the customer data to produce a plurality of clusters of customers with a plurality of features in common;

determining, by the processor, that a cluster represents a standard customer and storing a plurality of standard customer profiles based on the determined standard customers, wherein each of the plurality of standard customer profiles comprise a cluster and randomly selected identifying information;

generating a plurality of artificial customer profiles by combining randomly selected information from real customer profile data;

providing the plurality of artificial customer profiles to a cognitive system for generating synthetic transaction data based on the standard customer through a reinforcement learning model, wherein generating synthetic transaction data comprises:

providing standard customer transaction data representing a group of real customers having similar transaction data as a goal;

simulating a plurality of transactions via an action;

comparing the plurality of transactions with the goal;

providing feedback associated with the action based on a degree of similarity relative to the goal;

adjusting a policy based on the feedback;

repeating the simulating and adjusting of the policy until a degree of similarity between the plurality of transactions and the goal is higher than a predefined threshold; and

outputting the resulting plurality of transactions as the synthetic transaction data;

combine one of the plurality of artificial customer profiles with the simulated transaction data to form simulated customer data;

training, by the processor, a detection model for detecting activity based on the synthetic transaction data; and

distributing the detection model to computing devices over the network.

17. The computer program product of claim 16 , wherein the information for the plurality of customers comprises identifying information and transaction information, wherein the identifying information comprises a name, contact information, and finance information, and wherein finance information comprises one of a credit score, a wage, and a revenue.

18. The computer program product of claim 16 , wherein the method further comprises filtering the customer data prior to performing unsupervised learning; and wherein the filtering comprises a recency, frequency, monetary value analysis to group customers.

19. The computer program product of claim 16 , wherein the standard customer profiles comprise a plurality of data distributions for the plurality of features in common.

20. The computer program product of claim 16 , further comprising determining that a sub-cluster represents a standard customer by applying one or more rules.

21. The computer program product of claim 20 , wherein the one or more rules comprise a size determination indicating a minimum or maximum number of customers in a sub-cluster that is determined to be a standard customer.