Learn / Playbooks / Fraud and first-payment-default review

Fraud and first-payment-default review

First-payment defaults spiked last month. You need to know if it is fraud, a channel problem or a policy gap. Find where bad accounts come from: people, documents, branches and channels.

9 steps · 11 tools (2 free) · for risk analysts at banks and NBFCs

Tools you will use

This playbook is free to read. The prompt for each step is inside its tool. See the Pro tools.

Schema profile builderFree

Definition libraryFree

First-payment-default analysisFraud detection

Early-payment-default analysisFraud detection

Application fraud pattern detectionFraud detection

Identity and document anomaly checksFraud detection

Employer and salary verification checksFraud detection

Velocity checksFraud detection

Branch and DSA fraud patternsFraud detection

Channel, DSA and underwriter qualityUnderwriting policy and cut-offs

Watchlist and trigger automationRecovery and early warning

Check these first

Each tool asks the same questions and gives you a prompt to build whatever is missing.

Applications with first-payment outcome?

Have itDon't have it

Channel, branch and DSA fields on applications?

Have itPartly

Documents and identity check results?

Have itDon't have it

The steps, in order

Each step names the tool to open.

Set up

Tell the tools your table names

Applications, payments, channels and checks.

FreeSchema profile builderFreeDefinition library

Size the problem

First-payment default

How big, where, and since when.

First-payment-default analysis

Early-payment default

The next few instalments after the first.

Early-payment-default analysis

Look for fraud

Application fraud patterns

Repeated phones, addresses, devices and bank accounts.

Application fraud pattern detection

Identity and document anomalies

Edited or reused documents.

Identity and document anomaly checks

Employer and salary verification

Fake employers and inflated salaries.

Employer and salary verification checks

Velocity checks

The same detail used across many applications.

Velocity checks

Find the source

Branch and DSA patterns

Concentrations of bad accounts by source.

Branch and DSA fraud patternsChannel, DSA and underwriter quality

Triggers and watchlist

Stop repeat offenders at the door.

Watchlist and trigger automation

Check before you send

A cluster is confirmed by at least two independent signals.
First-payment default is split by channel and by week of sourcing.
Flagged accounts are reviewed by a person before any action.
You separate fraud from genuine inability to pay.

Warning signs

One DSA holds most of the bad accounts: that is a sourcing issue, not a model issue.

Fraud rules catch many accounts but all are good: rules are too tight.

What you hand over

A fraud and first-payment-default note naming the sources, the size of loss, and the new triggers to add.

In your profile

Once you are signed in, your profile shows which steps you can run with the tools you own, and which tools you still need.

Other playbooks

Monthly portfolio review Delinquency tracking Underwriting policy change Bureau data and scoring checks Scorecard build Model validation Early warning and leading indicators Collections strategy and agency performance Provisioning and ECL RBI reporting and asset classification Loss budget and stress testing Board and risk committee pack