You are here:
Monitor SLA Breach Prediction Card
Forecast SLA breach probabilities by using machine learning and real-time data analysis. Use the resulting scores, ranging from 0 through 100, to prioritize urgent tasks, manage critical issues, and improve service reliability.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, and Unlimited Editions with Einstein for IT Services add-on, and AI Accelerator for IT Services add-on. |
- From the App Launcher, find and select Incidents.
- From the Incidents page, open a record.
- In an incident record, navigate to the SLA Breach Score card in the side panel.
- Review the predicted score to determine the probability of an SLA breach. For example, a score of 0.08 indicates a very low risk.
-
In the Top Predictors list, identify the factors influencing the score. Common predictors
include:
- Subject and Description: Keywords that historically correlate with breaches.
- Impact: The correlation between the assigned impact level and the prediction.
- Owner History: The percentage of past records breached by the current owner.
-
Use the feedback icons to help refine the machine learning model:
-
Select the Thumbs Up icon if the prediction is accurate.
- Select the Thumbs Down icon if the prediction is incorrect.
-
Example:
Smith, an Incident Manager at Cumulus Bank, manages critical service disruptions. When a spike in database query timeouts affects trading portals, an incident record is created with these details.
- Incident Number: INC-4491
- Subject: Production Database Latency - AP-South Region
- Category: Software/Database
Smith opens the record and sees the SLA Breach Score card with a score of 82. This score indicates a high probability that the resolution time will exceed the 4-hour service level agreement to resolve the incident.
Smith reviews the top predictors list, powered by machine learning, to identify risk factors. Predictive AI identifies that the Subject and Description fields contain keywords such as production database and latency, which historically result in complex resolutions. Additionally, the owner history predictor shows that the generalist queue has a high breach rate for high-impact database issues.
To maintain service reliability, Smith escalates the incident to the Cloud Infrastructure team. Using real-time data analysis from the SLA Breach Score, Smith ensures experts prioritize the issue before the deadline. The team resolves the latency and maintains the bank's service commitments.
