An insurance company needs to evaluate applicant risk before issuing policies to prevent financial loss from high-risk drivers.

Customer submits application → historical data is analyzed → decision tree model evaluates behavior patterns → applicant is classified into a risk category → results are visualized in Tableau for decision-making.

• High Risk — Do Not Insure flagged
• Multiple at-fault accidents detected
• High number of claims identified
• Late payment behavior triggered alerts

• Increased claim payouts from high-risk drivers
• Poor pricing accuracy
• Higher loss ratios
• Increased fraud and risky policy approvals

• Underwriting: reviews flagged high-risk applicants
• Risk Management: monitors behavioral risk patterns
• Finance: adjusts pricing models
• Operations: implements stricter approval workflows

A decision tree machine learning model was deployed to automatically classify applicants based on behavioral risk indicators and output predictions into an interactive Tableau dashboard.

• Faster risk identification
• Improved underwriting accuracy
• Reduction in high-risk policy approvals
• Data-driven decision-making across departments

The system transforms raw applicant data into actionable intelligence, allowing insurers to proactively manage risk and optimize policy decisions.