Gurucul Machine Learning Model: Workflow with Classification Regression Tree
How does the Workflow with Classification Regression Tree machine learning model work, what does it do? This powerful model calculates a real-time risk score on the basis of multiple pieces of data including user outlier behavior percentage, resident user risk and reputation, and data or transaction risk classification.
During processing, if the user’s risk score value falls within a specific range, the user or entity is granted access, and if the risk score drops at any time, the user’s access is further subjected to defined policies. Classification regression trees are used to drive workflow decisions and other automation and orchestration actions and are a critical workflow component of Gurucul Risk Analytics.
Use Case: Dynamic Provisioning
Imagine using a risk score to determine whether to grant a user access to an application, a system, or a device. Wouldn’t it be a huge time-saver if you could auto-approve low risk access requests instead of manually granting such requests? Dynamic provisioning is just that. By risk-scoring users, their access devices and other factors, our customers eliminate the need for authentication via passwords, biometrics, and even, initially, requiring multi-factor authentication (MFA).
Gurucul Risk Analytics provides a risk score for all users and assets within the organization. Gurucul’s customers are able to examine a request from a low risk user for access to a low risk asset and simply grant that access automatically. The user doesn’t need to go through the typical approval process that most other organizations would need to go through.
If a user with a low-risk reputation initiates an application session from a recognized location with a known device, the run-time risk score would fall into a green/safe zone. As a trusted user, pass-through access would be granted without the need for any additional authentication.
If the same user, within the same session, then begins exhibiting abnormal behaviors, such as accessing unusual information, conducting anomalous transactions, etc., the users real-time risk score would increase. Once a user’s risk score exceeds pre-set thresholds and reaches the red/high-risk zone, automatic access responses are initiated. This includes enforcing MFA, locking the account, etc.
This machine learning model allows continuous monitoring of user behavior during a session to dynamically assess and adapt risk scores to enable real-time responses to anomalies, enabling the ability to further grant or remove a user’s access to networks and applications.
What are the Benefits of Workflow with Classification Regression Tree?
The benefits of the Workflow with Classification Regression Tree machine learning model are tactile and remarkable. With this powerful model, it’s possible to drive workflow decisions and other automation and orchestration. Machine learning-based behavior analytics extracts context from big data, rather than relying on simple rule and policy-based security controls.
Your opportunity to automate and orchestrate workflows is a phone call away. Contact us today!
The post Dynamic Provisioning: “Workflow Classification Regression Tree” appeared first on Gurucul.
*** This is a Security Bloggers Network syndicated blog from Blog – Gurucul authored by Jane Grafton. Read the original post at: https://gurucul.com/blog/workflow-classification-regression-tree