Anti-fraud & transaction protection
Every transaction.
Scored in under 50ms.
Aegis is a real-time AI fraud-detection platform for Bangladesh banks and MFS operators. A 3-layer cascade of 80+ deterministic rules, calibrated gradient-boosted models, and a deep ensemble decides every transaction before it touches the core banking system.
- Local CBS connector, no off-premises CBS data
- Post-quantum-ready transport (CRYSTALS-Kyber)
- English + Bengali analyst narratives
- Mapped clause-by-clause to BB CSF + BFIU
Synthetic-data benchmark: ROC-AUC 0.9955, PR-AUC 0.9666, F1 0.9580, FPR @ 95 % recall 0.0007. Production figures available under NDA.
01 / What is Aegis?
Aegis is KaritKarma's anti-fraud and transaction-protection platform for Bangladesh's regulated financial sector.
Every transaction passing through a participating bank or MFS operator is scored in real time by a 3-layer cascade: 80+ deterministic rules across 14 categories, a calibrated XGBoost + LightGBM trio, and a deep ensemble that combines a contrastive encoder, pgvector behavioural similarity, AGE graph traversal, and SHAP-based feature attribution. A stacking meta-learner resolves the cascade, isotonic calibration maps to probabilities, and dynamic decision bands publish APPROVE, REVIEW, STEPUP, or BLOCK in under fifty milliseconds.
Aegis ships with Bangladesh-specific intelligence: hundi corridor detection across six high-risk divisions, bKash and Nagad agent behavioural profiling, SIM-swap risk scoring against telecom signals, and the Bangladesh holiday calendar. It is mapped clause-by-clause to BB Cyber Security Framework v1.0 (Section 5 monitoring, Section 7 incident response) and BFIU AML/CFT (CTR, STR, SAR triggers). Deployment is on-prem, SaaS via a lightweight in-DC connector, or hybrid.
02 / Scoring cascade
Four layers.
One verdict.
Stops the moment it is sure.
Layers are independent and stop-on-decision. If L1 is confident, L2 and L3 never fire, so the cost of inference scales with actual uncertainty, not with traffic volume.
- L1<2ms
Rules gate
80+ deterministic rules across 14 categories. Sanctioned-party, velocity, country, BIN, time-of-day, MCC. Per-bank overrides. Stops the cascade on a high-confidence allow or block.
- 14 rule categories, velocity, identity, pattern, geography, regulatory.
- Per-bank thresholds without retraining a single model.
- Every decision linked to rule version + input snapshot.
- L22-5ms
Fast gradient boosting
XGBoost + LightGBM trio. Three-band output: clear, ambiguous, suspicious. Only ambiguous transactions escalate to L3 deep ensemble. Saves 70-80% of inference cost per transaction.
- XGBoost + LightGBM, calibrated per channel and per BIN.
- Three-band output gates the deeper, more expensive ensemble.
- Per-feature attribution shipped with every score.
- L315-25ms
Deep ensemble + stacking
Parallel components: contrastive encoder (ONNX), pgvector behavioral lookup, AGE graph traversal, SHAP explainer, combined by a stacking meta-learner. Isotonic calibration maps to probabilities. Dynamic decision bands per context.
- pgvector behavioural similarity on 768-d embeddings.
- AGE graph traversal for mule chains and ring detection.
- Stacked meta-learner with isotonic probability calibration.
- L4<24h
Human review queue
Analyst casework UI for STEPUP and BLOCK bands. Full transaction history, customer context, English plus Bengali narratives. Every disposition feeds back into rule and model registries.
- Bengali + English narrative per case.
- Customer 360, devices, sessions, prior alerts, dispute history.
- Feedback loop into model retraining and rule tuning.
03 / Bangladesh-specific intelligence
Patterns the rest of the world doesn't see.
Off-the-shelf fraud platforms model US card-present and US e-commerce. Aegis ships with detectors purpose-built for the typologies that actually move money illicitly through Bangladesh corridors.
Hundi corridor detection
Six high-risk divisions monitored: Chattogram, Brahmanbaria, Cumilla, Kushtia, Khulna, Bagerhat. Pattern: split transactions routed through informal money-transfer corridors to bypass reporting thresholds.
MFS agent split + float drain
Behavioural profiling on bKash and Nagad agent IDs. Pattern: agents structuring transactions just below KYC tiers across multiple customer accounts. Float drain detection on per-agent balance velocity.
SIM swap takeover
Telecom number-change events correlated with first-login geography. Pattern: number ported, then a large withdrawal or beneficiary change initiated within 24 hours.
Synthetic identity
Document-photo correlation across new accounts. Pattern: same selfie or NID image attached to multiple identities. pgvector image-embedding similarity on KYC artefacts.
Off-hours holiday spike
Bangladesh holiday calendar built in: Eid, Pohela Boishakh, government holidays. Pattern: spikes outside normal business hours during low-staffing windows.
BIN velocity anomaly
BIN-level velocity caps with per-merchant baseline. Pattern: a single BIN suddenly transacting at 10x its 30-day rolling baseline from a single merchant or merchant chain.
80+ rules across 14 categories, curated by Bangladesh financial-crime analysts.
Every rule is versioned, auditable, A/B-testable. Each one carries a tunable threshold so policy teams can dial sensitivity up or down without retraining a single model.
- versioned
- Every change produces a new signed version.
- auditable
- Decisions linked to rule + threshold + input snapshot.
- testable
- Shadow and champion-challenger before promotion.
- per-bank
- Overrides without forking the rule catalogue.
Velocity
12 rulesSingle-account transaction count > 20 / hour
Card-not-present aggregate > BDT 2L / day
Cross-border outbound > BDT 5L / 24h
Identity
9 rulesFirst-time merchant + first-time card combination
Device fingerprint mismatch against 90-day history
IP geography > 500km from last successful login
Pattern
11 rulesSequential round amounts (1k, 2k, 3k, ...)
Beneficiary account opened < 7 days before first inbound
Three failed-then-success pattern within 5 minutes
04 / How Aegis compares
Aegis vs. in-house, vs. SAS Fraud Management, vs. FICO Falcon.
The honest comparison. Global fraud platforms can be deployed in Bangladesh, but they ship blind to local typologies and their services engagements assume a six-month bank-IT runway. Aegis starts with the local fraud catalogue.
| Capability | Aegis | In-house | SAS Fraud Mgmt | FICO Falcon |
|---|---|---|---|---|
| Sub-50ms transaction scoring | Rare, usually 200ms+ batch | |||
| Bangladesh-specific fraud typologies (hundi, MFS agent, SIM swap) | Custom build, every time | |||
| Rules added without redeploy | Limited, SAS Visual Investigator | Limited, Falcon Rules Manager | ||
| Bengali narrative for analyst review | ||||
| Post-quantum-ready transport (CRYSTALS-Kyber) | ||||
| Federated learning across consortium banks | Flower 1.27, in pilot | Add-on, SAS Viya | ||
| Local CBS connector + offline failover | Per-bank | Custom services engagement | Custom services engagement |
Capability claims for SAS Fraud Management and FICO Falcon based on public documentation as of 2026 Q2. Speak to vendors directly for current product matrices.
05 / Integration path
Four steps from connector to inline blocking.
Bangladesh Bank does not permit core banking to be hosted off-premises. Aegis works with that constraint, not around it: a thin in-DC connector streams transactions out, decisions come back inline.
- Step 01
Deploy the connector
Drop the Go CBS Connector inside the bank data centre. Streams transactions over gRPC + Kafka. No outbound data movement beyond the agreed envelope.
- Step 02
Shadow-mode validate
Run Aegis in pure observe mode against live traffic for 2-4 weeks. Calibrate thresholds against the bank's actual false-positive tolerance, with daily backtests.
- Step 03
Enable inline blocking
Promote from REVIEW-only to STEPUP and BLOCK bands once shadow metrics meet the agreed FPR and TPR targets. Per-channel, per-product rollout.
- Step 04
Plug regulator feeds
Wire CTR, STR, SAR alerts to your goAML pipeline and to the BFIU reporting handler. Audit trail and reason-code citation per filing.
06 / Regulatory mapping
Mapped clause-by-clause to Bangladesh Bank and BFIU.
Aegis isn't compliance-adjacent. Every capability is mapped to a specific clause your auditors already cite, so the regulatory evidence package writes itself.
SIEM and continuous monitoring
Inline transaction-stream monitoring with structured event capture and 12-month hot retention, mapped to Section 5 monitoring controls.
Incident response
Casework, escalation, and audit-log export aligned to the 72-hour incident-notification window required by BB CSF Section 7.
CTR, STR, SAR triage
Threshold-aware triggers for CTR (cash transactions > BDT 10 lakh), structuring (cumulative daily reaches 80-99 % of CTR), and SAR (3+ high-severity rules within 7 days on one account).
Digital transaction oversight
Sub-50ms inline scoring across MFS, card, and account-to-account flows so digital transactions are monitored inline, not in next-day batch.
07 / What runs under the hood
The stack is the moat.
Aegis reuses around 90 % of its production tech from KaritKarma's portfolio: NewsForge vector brain, IntraPay payment primitives, Hold.bd Clean-Architecture .NET, Wenme identity, Darwan RBAC.
- ConnectorGo, gRPC, Kafka, zap, pgx
- IntelligencePython, FastAPI, asyncpg, XGBoost + LightGBM, ONNX
- Platform.NET 10, Clean Arch, MediatR, Serilog + Seq
- FrontendNext.js 16, React 19, Turborepo, TanStack Query
- DataPostgreSQL 18, pgvector, AGE, TimescaleDB, Redis
- TransportmTLS, CRYSTALS-Kyber + Dilithium, AES-256-GCM
08 / Frequently asked
Questions banks and MFS operators ask first.
Each answer mirrors the on-page text in our structured-data payload, so AI answer engines and audit reviewers see the same wording.
- 01What is Aegis?
- Aegis is KaritKarma's real-time AI fraud-detection platform for Bangladesh banks, NBFIs, and mobile financial service operators. It scores every transaction in under 50 milliseconds using a 3-layer cascade of 80+ deterministic rules, calibrated gradient-boosted models, and a deep ensemble that includes pgvector behavioural lookup and AGE graph traversal. It ships with Bangladesh-specific intelligence modules for hundi corridors, MFS agent fraud, SIM swap, and the Bangladesh holiday calendar, and is mapped clause-by-clause to the BB Cyber Security Framework and BFIU AML/CFT guidelines.
- 02What is the end-to-end scoring latency?
- Aegis targets sub-50 millisecond p95 end-to-end scoring. Layer 1 (rules gate) completes in under 2 ms. Layer 2 (fast gradient-boosting trio) adds 2 to 5 ms. Only ambiguous transactions escalate to Layer 3 (deep ensemble + stacking meta-learner + isotonic calibration), which completes in 15 to 25 ms. The cascade short-circuits the moment a layer is confident enough to act, so deeper analysis runs only when it actually adds signal.
- 03Can fraud rules be added or tuned without redeploying?
- Yes. Every rule is versioned, auditable, and A/B-testable. Policy teams can dial thresholds up or down, promote rules through shadow and champion-challenger evaluation, and roll back on a click, all without retraining a model or shipping a new build. Each rule change produces a new signed version, and every decision is linked to the rule version, threshold, and input snapshot for full audit.
- 04Does Aegis support Bangladesh Bank Cyber Security Framework monitoring requirements?
- Yes. Aegis is mapped clause-by-clause to BB Cyber Security Framework v1.0. It satisfies Section 5 (SIEM and continuous monitoring) through inline transaction-stream monitoring with structured event capture, and Section 7 (incident response) through casework, escalation, and audit-log export aligned to the 72-hour incident-notification window. It also satisfies BFIU AML/CFT transaction monitoring requirements with CTR, STR, and SAR triage.
- 05How does Aegis integrate with our core banking system?
- A lightweight Go connector agent is deployed inside the bank data centre, since Bangladesh Bank does not permit CBS to be hosted off-premises. The connector streams transactions to the Aegis scoring service over gRPC with mTLS (post-quantum-ready via CRYSTALS-Kyber from IntraPay), and includes local failover with cached rules for offline scoring. CBS adapters are pluggable, with initial support for Temenos T24 REST callback in place and Finacle and Flexcube on the roadmap.
- 06What is the deployment model: SaaS, on-prem, or hybrid?
- All three. SaaS mode keeps the scoring brain in KaritKarma's APNIC AS 64005 Tier-3 data centre with only the lightweight connector inside the bank. On-prem mode packages the entire stack as a Docker Compose appliance for banks that require full premises deployment. Hybrid mode keeps local failover and cached rules inside the bank while the cloud handles heavy ML and cross-bank consortium intelligence.
Protect your customers
9.3% MFS fraud rate.
Zero dedicated solutions.
Bangladesh processes 12 billion MFS transactions a year with no dedicated fraud-detection platform calibrated to local typologies. Aegis fills that gap with production-grade AI built on a stack already deployed at aegis.karitkarma.com.
Bring Aegis into your fraud-ops stack.
Get a personalized walkthrough of Aegis with one of our specialists. No commitment required.