Predicting missing the Service-Level Agreement
Pega Process AI™ can help to distinguish regular from complex claims. Complex claims often escalate into a lengthy process, which is costly and leads to a bad customer experience. The distinction lets you detect these claims early and address them at once.
Learn how to create a prediction that aims to identify cases that are likely to miss their deadlines and route them to a senior employee to handle them more efficiently and improve the customer experience.
Video
Transcript
This demo shows you how to use adaptive models to predict missing the Service-Level Agreement (SLA).
U+ Insurance uses Pega Platform™ for case management. An incoming car insurance claim is straight through processed, or routed to a claims operator, who approves or rejects the claim to resolve the case.
A case is escalated to an expert when the claim is not completed in the allotted time for regular processing.
In the current configuration, claims that exceed 45000 are considered highly complex and are always investigated by an expert as a precaution.
However, decisioning using hard business rules, like in this case based on a simple cutoff value is not efficient, because even cases that exceed 45000 can be often resolved on time in the regular claims process. As a result, the experts consequently spend valuable time on relatively simple claims.
Process AI can help optimize the process by predicting the likelihood that a case is resolved before the deadline in the regular workflow and otherwise, route it to an expert irrespective of the cause of the complexity of the claim. First, it is an Application Developer's task to create a Boolean outcome field. It serves the adaptive model as the outcome field and allows it to distinguish cases that missed the SLA. You add the outcome field in the case type data model settings to make it available in that case type.
Next, to allow the model to learn from future outcomes, in Goal & deadline settings of the case type, the Application Developer configures a condition that automatically sets the outcome as missed when the deadline expires. Finally, a Data Scientist creates a case management prediction that calculates the propensity of whether the case is likely to miss the SLA.
Process AI offers a wizard to create Missing Service-Level Agreement (SLA) predictions.
The Outcome field reflects the Boolean field that the Application Developer creates. This associates the prediction with the case type.
Next step for the Data Scientist is to add potential predictors. Best practice is to include many unrelated fields, including the claim properties. It is also important to exclude predictors that are irrelevant and do not have any predicting power, like ChassisNo, CustomerID, CustomerPhoto, Name, PhoneNo, PolicyNo, and RegistrationNo.
The adaptive model learns from previous cases and automatically activates predictors that perform above a threshold and deactivates predictors when their performance drops over time. The prediction is ready to be implemented in the Claims case case type by an application developer.
In the current configuration, the Decide complexity decision step categorizes claims as low or high complexity depending only on the claimed amount. As a result, claims that exceed 45000 are categorized as complex.
This condition requires an edit to meet the new business requirement that the routing decision is based on the propensity calculated by the Missing SLA prediction. To categorize a claim as a high complexity claim in the Decide complexity decision step, the propensity to miss the SLA needs to exceed a threshold. In this case: 0.4.
When a claims operator handles a claim, the case status changes to Resolved-Completed or Resolved-Rejected, and the outcome of the case maps to the alternative label (MissedSLA = False) for the prediction. When a complex claim misses the deadline, the outcome of the case maps to the target label (MissedSLA = True) for the prediction. The model learns using this information and as a result, depending on the outcome, the missing SLA propensity for a similar case in the future increases or decreases.
A claim with a high propensity to miss SLA is immediately routed to an expert. The claim is routed to the regular workflow when the expert assesses the claim and does not consider it a complex case. This reassignment allows the adaptive model to learn from cases that are incorrectly routed to the expert.
An adaptive model is created for each primary and alternative stage in the case type. A decision request in a stage uses the model that is specific to that stage to calculate the propensity.
At the very beginning, the models have no predictive power. The models learn and self-optimize with every captured case outcome.
This demo has concluded. What did it show you?
- How to create a missing SLA prediction.
- How to implement a missing SLA prediction to improve efficiency.
This Topic is available in the following Modules:
If you are having problems with your training, please review the Pega Academy Support FAQs.
Want to help us improve this content?