Managing Alerts Through AI Helps Prevent Major Incidents for a Health Insurance Company

Business Objective

Our client is a major provider of health insurance plans in the US. Its command center team receives over 400,000 alerts in a year. The current rule-based approach of categorizing alerts into potential incidents required some adjustment, as the client was missing on identifying a significant number of (high risk) alerts that led to major incidents.

More specifically, the client wanted to:

  • Develop a predictive model to assign a risk score to alerts and prevent the likelihood of major incidents that may cause business disruption
  • Recommend the right call-to-action framework to send critical alerts to the command center
  • Linking alerts to major incidents/problems as the mapping was not readily available
  • A high correlation of alerts with each other posed challenges in training the model

Solution Methodology
  • Performed a detailed analysis to establish the linkage across data sources to define the target variable (major incident) appropriately
  • Tested specific hypotheses with the available data, through features related to alert source, alert application (member portal, provider application, etc.), alert type (CPU check, memory check, etc.), alert received time, alert duration, and the number of events
  • Developed a predictive model using the Random Forest algorithm to assign a risk score
Business Impact
  • The developed model is currently being used to tag high-risk alerts and guide alert handling team with tip-offs to resolve the issue quickly

  • The algorithm-based risk score identifies alerts linked to major incidents more accurately

  • The typical nature of predictive variables in the model (alert type, alert duration, no. of events) made the solution very scalable by applying it to other applications, not in the scope

Copyright © 2023 Tiger Analytics | All Rights Reserved