Lab №02 · Fintech & Banking

Fintech
Lab.

Products shipped
64since 2016
Active engineers
78FT
Annual volume
₹4.2Tprocessed
Audits passed
14no findings

Banks lose to fintechs because their software cycle is measured in quarters, not days. We bridge that gap for the banks we serve — core banking integration, AI risk models, and onboarding pipelines built to the same standards as their compliance teams demand, shipped at the pace their product teams need. Axis, Bajaj, IDFC First, HDFC, and Union Bank of India all run software we engineered.

What we build inside
the Fintech Lab.

Six practices · One team
P.01

Fraud & AML

Real-time transaction scoring, network analysis, mule detection. XGBoost ensembles tuned per channel. Sub-100ms scoring at 1.8M tx/day.

XGBoostKafkaGraph ML
P.02

Credit Risk Models

PD, LGD, EAD modeling for retail, MSME, and corporate. PSI/KS monitoring, vintage analysis, monthly recalibration cycles.

PSI / KSCatBoostIFRS 9
P.03

KYC & Onboarding

Aadhaar e-KYC, OCR pipelines, face liveness, dedup engines. 90-second onboards across 14 deployments.

AadhaarOCRFaceMatch
P.04

Core Banking Bridges

Finacle, TCS BaNCS, Flexcube integrations. Account, transaction, GL, and limit APIs — wrapped, throttled, audited.

FinacleTCS BaNCSFlexcube
P.05

Payments & Settlement

UPI, IMPS, NEFT, SWIFT MT & MX (ISO 20022), card switching. Reconciliation engines tested to T+0 close.

UPIISO 20022SWIFT MX
P.06

Trading Infrastructure

FIX 4.4/5.0 connectivity, OMS adapters, low-latency market data ingestion. Sub-millisecond paths where they matter.

FIX 4.4OMSDPDK

This quarter's
featured work.

CS-2026-007
↳ Transaction anomaly cluster · 1.8M/day stream · live
cluster · 94.2% recall
Stream
1.8M / day
Recall
94.2%
FPR
0.4%
Featured · Fintech · Jan 2026

Real-time fraud detection across 1.8M daily transactions.

Axis Bank's previous fraud engine fired on too many legitimate transactions and missed coordinated mule networks entirely. We rebuilt the scoring stack around an XGBoost ensemble with a graph-features layer for entity resolution. 94.2% recall at 0.4% false-positive rate, scoring at p99 < 80ms.

94.2%
Recall on held-out
0.4% FPR
Down from 3.1%
80ms p99
End-to-end latency

Standards we
engineer to.

↗ Compliance dossier on request

Fintech compliance posture.

All current as of Q1 2026
PCI-DSS v4.0
Since 2018
Card data handling. SAQ-D level. Annual external assessment with named QSA.
SOC 2 Type II
Since 2020
Security, availability, confidentiality, processing integrity. Public report under NDA.
ISO 27001
Since 2019
Information security management. Certified across both Indore and San Jose offices.
RBI-aligned
Since 2017
Cyber-security framework circulars, data localization, RBI cloud guidelines.
ISO 20022
Since 2022
MX message formats, SWIFT CBPR+, payment market practice. Migration tooling shipped.
GDPR
Since 2018
EU-resident customer flows for two UK fintech clients. DPIA templates, residency builds.
DPDP Act
Since 2024
India's Digital Personal Data Protection Act. Consent, deletion, breach notification workflows.
NPCI / UPI
Since 2018
Empanelled with three banks for UPI handoff. UPI 2.0 + 3.0 capabilities (recurring, IPO, etc).

Ten years of
fintech engineering.

Selected milestones
2016
Lab founded.
First six fintech engineers hired from banking IT. Karan joins from a Mumbai private bank. First UPI handoff PoC built in Q4.
Indore
2018
PCI-DSS certified.
First card-data engagement. Annual external assessment relationship begins with a named QSA. SAQ-D level achieved.
SAQ-D
2019
First core banking bridge.
Finacle integration for a Tier-2 Indian bank. Account, transaction, GL APIs. Anil joins from Infosys to lead the practice.
Finacle · India
2020
RBI sandbox participation.
Co-applicant on two RBI regulatory sandbox cohorts (account aggregator, MSME credit). SOC 2 Type II achieved.
SOC 2
2022
First ML in production.
Bajaj Finserv credit-risk model deployed. 0.91 AUC at T+30. Lab's risk-modeling playbook formalized.
0.91 AUC
2024
IDFC First onboarding.
90-second open-to-KYC flow shipped. eKYC + face liveness + Aadhaar dedup. Replicated for two more banks in 2025.
90 sec median
2026
Axis Bank fraud at scale.
94.2% recall, 0.4% FPR, 1.8M tx/day. ISO 20022 migration tooling shipped to two clients. Lab now 78 engineers.
Q1 · live

Hand us the sketch.
Claim the spotlight.

Sales · +1‑408‑409‑7548 · sales@emorphis.com
Start a project

The fintech
stack we run.

As of 2026.03
F.01

Reconcile or don't ship.

Every payment, every settlement, every ledger entry has a reconciliation harness that runs before code merges. If accounts don't balance to the rupee, the test fails.

F.02

Idempotency is non-negotiable.

Every monetary endpoint takes an idempotency key. Every retry is provably safe. We've never double-debited in production. Not once.

F.03

Models with calibration plots.

Every credit model ships with a calibration plot, a PSI dashboard, and a documented monthly recalibration trigger. The risk team owns the dashboard.