System and method for automated access request recommendations
Systems and methods for embodiments of graph based and machine learning artificial intelligence systems for generating access item recommendations in an identity management system are disclosed. Embodiments of the identity management systems disclosed herein may utilize a graph based approach, a machine learning based approach, and hybrid combinations thereof for generating access item recommendations.
1. A method, comprising:
obtaining data from an identity management system, the obtained data relating to identities and entitlements of the identity management system;
determining feature data from the obtained data, the feature data corresponding to the identities and entitlements;
applying the feature data to a graph database query configured to determine whether a target identity in the identity management system should have access to access items in the identity management system;
applying the feature data to a machine learning model trained to determine whether the target identity in the identity management system should have access to access items in the identity management system; and
based on outputs of the graph database query and the machine learning model, generating personalized access recommendations for the target identity that the target identity obtain access to specific access items of the identity management system.
2. The method of claim 1 , further comprising, responsive to the generated personalized access recommendation, receiving an access request from the target identity for access to the access item.
3. The method of claim 2 , further comprising, responsive to receiving the access request from the target identity, initiating an approval process for access to the access item by the target identity.
4. The method of claim 1 , wherein the feature data is only applied to the machine learning model if output from the graph database query is not satisfactory.
5. The method of claim 1 , wherein the outputs of the graph database query and the machine learning model are weighted, and wherein personalized access recommendations are generated based on a combination of the weighted outputs of the graph database query and the machine learning model.
6. A method, comprising:
obtaining data from an identity management system, the obtained data relating to identities and entitlements of the identity management system;
determining feature data from the obtained data, the feature data corresponding to the identities and entitlements;
embedding the feature data to transform the feature data to a more usable form;
providing the embedded feature data as input data to a machine learning model;
generating, using the machine learning model, an output score, the output score relating to the confidence that a target identity in the identity management system should have access to an access item; and
responsive to the output score reaching a threshold value, generating a personalized access recommendation for the target identity that the target identity obtain access to the access item.
7. The method of claim 6 , wherein the obtained data includes:
historical user-initiated access item requests;
certification data relating to granted access to a role; and
logs from data harvesters of the identity management system.
8. The method of claim 6 , further comprising, responsive to the generated personalized access recommendation, receiving an access request from the target identity for access to the access item.
9. The method of claim 6 , further comprising, responsive to receiving the access request from the target identity, initiating an approval process for access to the access item by the target identity.
10. A system, comprising:
a processor; and
a non-transitory computer readable medium including instructions for:
obtaining data, the obtained data relating to identities and entitlements of an identity management system;
determining feature data from the obtained data, the feature data corresponding to the identities and entitlements;
applying the feature data to a graph database query configured to determine whether a target identity in the identity management system should have access to access items in the identity management system;
applying the feature data to a machine learning model trained to determine whether the target identity in the identity management system should have access to access items in the identity management system; and
based on outputs of the graph database query and the machine learning model, generating personalized access recommendations for the target identity that the target identity obtain access to specific access items of the identity management system.
11. The system of claim 10 , wherein the instructions are further for, responsive to the generated personalized access recommendation, receiving an access request from the target identity for access to the access item.
12. The system of claim 11 , wherein the instructions are further for, responsive to receiving the access request from the target identity, initiating an approval process for access to the access item by the target identity.
13. The system of claim 10 , wherein the feature data is only applied to the machine learning model if output from the graph database query is not satisfactory.
14. The system of claim 10 , wherein the outputs of the graph database query and the machine learning model are weighted, and wherein personalized access recommendations are generated based on a combination of the weighted outputs of the graph database query and the machine learning model.
15. A system, comprising:
a processor; and
a non-transitory computer readable medium including instructions for:
obtaining data, the obtained data relating to identities and entitlements of an identity management system;
determining feature data from the obtained data, the feature data corresponding to the identities and entitlements;
embedding the feature data to transform the feature data to a more usable form;
providing the embedded feature data as input data to a machine learning model;
generating, using the machine learning model, an output score, the output score relating to the confidence that a target identity in the identity management system should have access to an access item; and
responsive to the output score reaching a threshold value, generating a personalized access recommendation for the target identity that the target identity obtain access to the access item.
16. The system of claim 15 , wherein the obtained data includes:
historical user-initiated access item requests;
certification data relating to granted access to a role; and
logs from data harvesters of the identity management system.
17. The system of claim 15 , wherein the instructions are further for, responsive to the generated personalized access recommendation, receiving an access request from the target identity for access to the access item.
18. The system of claim 15 , wherein the instructions are further for, responsive to receiving the access request from the target identity, initiating an approval process for access to the access item by the target identity.