B

Baloise Fraud Shield

by Baloise · Primary insurer

no ratings

Anomaly detection platform that scores claims for fraud likelihood using network analysis and behavioural patterns, flagging suspicious cases for special investigation.

Anomaly detectionMachine learning and predictive analyticsMotor vehicle insuranceProperty insuranceLiability insurance

2 free views left this month

Business context

Purpose of use

Detect and prevent fraudulent claims earlier in the lifecycle.

Value chain steps
Fraud detection and preventionClaims management
Insurance branches
Motor vehicle insuranceProperty insuranceLiability insurance
Application scope
Internal only
Business criticality
Business critical
Country or market unit
SwitzerlandBelgium

Value and impact

Added value category
Cost reductionRisk reduction
Added value estimation

Targets a measurable uplift in detected fraudulent claims value.

Estimated weekly case volume
6,200
Time to value (months)
8
Competitive advantage gain

Graph-based network detection of organised fraud rings.

Quality gain

Higher precision reduces false accusations against honest customers.

Technical details

AI category
Anomaly detectionMachine learning and predictive analytics
AI platform provider
Databricks Mosaic AI
Cloud provider
Amazon Web Services
Technology stack
DatabricksSparkGraph analytics
Interfaces used

Claims system event stream

Architectural insights

Streaming feature pipeline feeding a gradient-boosted scoring model.

Automation level
3/5
Estimated IT difficulty
4/5

Compliance and governance

EU AI Act risk category
High risk
EU AI Act role
Deployer
Relevant policies
EU Artificial Intelligence ActSwiss Federal Act on Data Protection
Responsibilities

Special investigations unit reviews every flagged case before action.

Data used

Claims data, payment records, third-party fraud indicators.

Metadata

Development type
Minimum viable product
Go-live date
Dec 1, 2024
License model
Hybrid

Community

Average rating

0.0 · no ratings

Comments

Log in to join the discussion.

No comments yet. Be the first to comment.

Related solutions

Z
Zurich Claims Intelligence

by Zurich Insurance Group

AI-driven claims triage and automated damage assessment for motor and property claims. The system classifies incoming claims, estimates severity, and routes complex cases to specialists while straight-through processing simple ones.

Machine learning and predictive analyticsComputer visionMotor vehicle insuranceProperty insurance
no ratings9158
C
CSS Health Document AI

by CSS Versicherung

Document understanding pipeline that reads incoming medical invoices and reports, extracts structured data, and validates them against policy coverage automatically.

Computer visionNatural language processingSupplementary health insuranceDaily sickness allowance insurance
no ratings9158

Computer vision model that estimates property and natural-hazard damage from customer-submitted photographs to accelerate settlement after weather events.

Computer visionMachine learning and predictive analyticsProperty insuranceNatural hazards insurance
no ratings7158