GGenerali CentralExecutive Cockpit

Fraud & SIU 360

Fraud, waste & abuse leaks 8–10% of claim payouts industry-wide — the number to lead with. This view sets out the motor-vs-health fraud types, the SIU case pipeline from flagged to recovered, the detection-method mix (SIU · rules · AI · network · IIB), and readiness for the IRDAI Fraud Monitoring Framework 2025. Company-specific save and catch figures are MODELED targets, peer-benchmarked.

Generali Central Insurance Company Limited · FY25 (Mar'25, audited)
Mid-tier private multiline general insurer — Top-10 private (rank ~10)
2,644 employees · 167 branches · 21,000+ agents
🤖 Digital, AI & fraud controlStep 2 of 6 · fraud & SIU: 8-10% leakage, detection & recoveryAI Use CasesClaims & Renewals 360All journeys
🌐 Enterprise 360 modules· on Fraud & SIU 360Browse all 51 views ▾
Todayyour decision queue📨 Activity & Digestaudit trail · @mentions🧭 360 Directoryall views by persona🗺 Guided Journeyspersona flows · step-by-step🛰 Control Towercommand center🎯 Strategy & Goals4 pillars · OKRs💎 Value Creation Planturnaround · value🤖 AI Use Casesrecommend & act🌐 Enterprise 360the consolidated pane📈 New Business & Underwriting 360funnel · forecast🚗 Motor 360OD vs TP · classes · claims🏥 Health 360retail vs group · ICR · cashless🛡 Fraud & SIU 360leakage · detection · recovery🛰 Market & Industry Intelsignals · growth initiatives🏛 Company Hierarchyorg · lines · entities🗂 Org Roll-up 360zone · line · branch📍 Branch & Distribution 360branch twin · sourcing · zones👥 Channels & Customers 360channels · cross-sell🧩 Customer Mastergolden record · MDM🧾 Quote & Proposal 360proposals by line🔄 Quote-to-Premium 360quote-to-premium cycle🔁 Claims & Renewals 360claims · cashless · renewals🔧 Case / Project 360delivery · case handling👷 Workforce 360people · productivity🏷 Products & Lines 360products · loss ratio🧩 Programs & Digital 360PMO · workstreams · go-live🤝 Growth Initiatives 360initiatives · investment · ROI🚪 Turnaround & Growthcombined ratio · solvency · ₹10k cr🚚 Reinsurance & Network 360reinsurers · hospitals · garages💰 Finance 360P&L · combined ratio💵 Cash 360premium · float · investments🧬 Ontology & Meshlogical layer · data products Evidencedrill-to-record · export🩺 Data Healthfreshness · lineage🕸 SciKIQ Data Fabriclive catalog · PII · scans🧠 SciKIQ Fabric Mapthe whole architecture📄 Policy 360live policies · lapse score🧾 Claim 360live claims · severity · fraud🏥 Hospital & Provider 360network · anomaly score🤝 Agent & Broker 360distribution · portfolio quality Compliance 360KYC · PII · obligations🎛 Simulationdeterministic what-if📑 Document Intelligencebills & estimates → structure🔌 Connectorswhat is actually wired📋 Underwriting & Pricing AIrules decide · model explains🧭 Coverage Reasoningliability · payable · rules🔁 Lapse, Retention & Sales AInext best action · cross-sell · leads🕸 Fraud Network Analysishubs · co-occurrence · concentration Decision Stacksee → predict → act🤖 AI Agentic Workforce10 always-on agents📚 Data Catalogterms · CDEs · glossaries
● LiveBuilt forHead — Claims & Fraud Control· the SIU caseload & recoveryChief Risk Officer· leakage, catch-rate & FMF-2025 readinessCFO / Board· ₹ saved as a loss-ratio lever

Every point of leakage recovered flows straight to the loss ratio. Industry FWA runs 9% of claim payouts and ~15% of health claims carry a fraud element. The case table below is illustrative; the gold "modeled" figures (savings, catch-rate, SIU build-out) are peer-benchmarked targets, not claimed actuals.

Data backing: fraud_metric (leakage · health-fraud share · flagged · savings · catch-rate · SIU · FMF readiness) · fraud_case (12 illustrative SIU cases — type · line · method · ₹ claimed/saved · AI score · status)
9%
Claims leakage (FWA)
target 6% · industry 8–10%
₹78 Cr
Fraud savings
modeled · target ₹120 Cr
62%
Catch-rate (pre-pay)
modeled · target 80%
The number to lead with

9% of claim payouts lost to fraud, waste & abuse

BCG × Medi Assist (2025) put FWA leakage at 8–10% of payouts industry-wide; in health alone that is ₹8,000–10,000 Cr a year. Motor is the largest fraud-exposed general line; health the fastest-rising.

Claims leakage today
9%
of claim payouts (modeled at industry mid-point)
Target 6% — closing 3 pts of leakage

Motor fraud

6 sample cases

Staged accidents, inflated repairs, fake TP injury (MACT), phantom vehicles, total-loss/salvage, backdated e-policies. The Supreme Court flagged a 'wide racket' of fabricated motor-accident claims (Feb 2026).

Health fraud

6 sample cases

Inflated/upcoded hospital bills, impersonation, provider collusion, PED non-disclosure, ghost billing, fake PMJAY/scheme claims. ~15% of health claims carry a fraud element.

The SIU caseload

Case pipeline — flagged → investigating → confirmed → recovered

An illustrative snapshot of the Special Investigation Unit book. Bars show ₹ claimed by stage with the recovered/prevented portion in green; amounts in ₹ lakh.

Flagged1 case
₹5.2 L claimed · ₹3.9 L saved
Investigating2 cases
₹21.9 L claimed · ₹6.0 L saved
Confirmed5 cases
₹13.3 L claimed · ₹13.3 L saved
Recovered4 cases
₹13.7 L claimed · ₹11.0 L saved
CaseLineFraud typeDetectionClaimedSavedAI scoreStatus
MOT-FR-2203MotorFake Third-Party (TP) injuryNetwork analytics₹12.5 L₹0.0 L0.88Investigating
HLT-FR-3303HealthProvider collusion (network hospital)Network analytics₹9.4 L₹6.0 L0.91Investigating
MOT-FR-2205MotorTotal-loss / salvage fraudRed-flag rules₹6.0 L₹4.5 L0.76Recovered
HLT-FR-3305HealthGhost / phantom billingAI score₹5.2 L₹3.9 L0.79Flagged
MOT-FR-2201MotorStaged accident (organised ring)SIU₹4.8 L₹4.8 L0.92Confirmed

Sample of 12 cases: ₹54.1 L claimed, ₹34.2 L saved (recovered or prevented pre-payment). Claims scoring above the AI threshold (0.75) auto-route to the SIU. This table is illustrative — portfolio-level savings are the modeled ₹78 Cr below.

AI · pre-payment

Claim fraud triage — score it before you pay it

Live AI

Catch-rate only moves if suspicion is raised BEFORE payment. This scores a live claim against the SIU case book above — band and routing computed in code from the fraud-score threshold, not left to the model.

Claim under triage

Azure OpenAI scores the claim against the 12 seeded SIU cases; the band and SIU routing are derived in code from the threshold in fraud_metric — the model does not route claims.

Pick a scenario or write your own claim, then run the triage — you get a fraud score, the red-flag indicators it matched, what to collect before deciding, and the closest confirmed cases from the SIU book. Two presets are ordinary, genuine claims; they should score low.

How it's caught

Detection-method mix

Five detection engines: SIU field investigation, red-flag business rules, AI/ML scoring, link/network analytics, and cross-insurer IIB matches. Ranked by ₹ saved in the sample.

AI score · 3 cases₹7.8 L
Red-flag rules · 3 cases₹7.7 L
SIU · 2 cases₹6.9 L
Network analytics · 2 cases₹6.0 L
IIB match · 2 cases₹5.8 L

AI scoring and red-flag rules screen the widest net pre-payment; SIU and network analytics carry the high-value organised-ring cases.

Where the fraud sits

Motor vs Health

Motor is the largest fraud-exposed general line by count; health carries the higher-value collusion and billing cases.

Motor6 cases
Claimed
₹29.5 L
Saved
₹15.0 L
51% of claimed value saved in-sample
Health6 cases
Claimed
₹24.6 L
Saved
₹19.2 L
78% of claimed value saved in-sample
Regulatory & capability

IRDAI Fraud Monitoring Framework 2025 readiness

The FMF is effective 1 April 2026: a mandatory Fraud Monitoring Committee & Unit, insurer-specific red-flag indicators, and mandatory participation in the IIB Fraud Technology Framework (Caution Repository of blacklisted providers + a cross-insurer policyholder ID).

FMF-2025 readiness
Modeled
70%
to 100% before the 1 Apr 2026 effective date
The five mandated capabilities
  • Fraud Monitoring Committee + dedicated Fraud Monitoring Unit
  • Insurer-specific Red-Flag Indicator library (motor + health)
  • Mandatory IIB Fraud Technology Framework participation
  • Caution Repository — blacklisted hospitals / vendors / fraudsters
  • Unique cross-insurer policyholder identifier
Fraud savings (recovered + prevented)
Modeled
₹78 Cr
target ₹120 Cr
Fraud catch-rate (pre-payment)
Modeled
62%
target 80%
Fraud cases flagged (FY)
Modeled
4,200
target 6,000
SIU headcount
Modeled
34
target 60 (FMF unit)

The prize: lifting fraud savings toward 78 → ₹120 Cr is a direct loss-ratio lever. The capability path is peer-proven — Generali Group has run Shift Technology AI fraud detection since 2016 (typically +20–30% detection uplift); Star Health reports +35% YoY on FWA savings. These are the benchmarks behind the modeled targets.