BUSINESS REQUIREMENTS DOCUMENT (BRD)

Project: FinTech Fraud Detection & Risk Analytics

Document Info	Details
Document Version	1.0
Author	Priyanka Chaudhari, Business Analyst
Date	2024-Q1
Status	Approved
Project Sponsor	Head of Risk & Compliance
Last Reviewed	2024-03-01

1. EXECUTIVE SUMMARY

A mid-size FinTech payment processor is experiencing a rise in fraudulent transactions with no systematic detection or risk-scoring framework in place. Fraud losses are growing quarter-over-quarter and the Risk & Compliance team lacks the analytical infrastructure to identify high-risk merchants, flag suspicious customers, or quantify financial exposure by segment. This project delivers an end-to-end fraud analytics solution, from raw transaction data through SQL-based risk analysis to an executive Power BI dashboard, enabling data-driven fraud control decisions.

2. BUSINESS OBJECTIVES

1. Identify and quantify fraud exposure by merchant, category, geography, and time-of-day

2. Produce a merchant risk scorecard (HIGH/MEDIUM/LOW) to guide rule-engine development

3. Deliver monthly trend visibility to track fraud rate movement over time

4. Profile high-risk customers for Customer Due Diligence (CDD) review queue

5. Provide actionable rule recommendations to reduce fraud exposure by 40-50%

3. PROBLEM STATEMENT

Current State:

- No centralized fraud detection framework exists

- Risk team reviews transactions manually, slow, inconsistent, non-scalable

- No merchant-level or customer-level risk scoring

- No trend tracking, leadership cannot see fraud rate movement month-to-month

- Estimated annual fraud loss: $300K-$500K with no quantified breakdown

Desired State:

- SQL-based analytical framework with 8+ risk queries and a merchant risk view

- Executive Excel workbook: KPI summary, category analysis, amount buckets, monthly trend

- Interactive Power BI dashboard with drill-through by merchant, region, and time

- Documented recommendations for rule-engine implementation

4. STAKEHOLDERS

Stakeholder	Role	Responsibility	Priority
Head of Risk & Compliance	Project Sponsor	Approve scope, accept deliverables	High
Fraud Analytics Lead	Primary User	Use scorecard for rule-engine specs	High
Finance Director	Secondary User	Review P&L fraud exposure reporting	Medium
Product Manager	Secondary User	Consume requirements for alert features	Medium
Engineering Lead	Tertiary	Implement rule-engine from recommendations	Medium
Legal & Compliance	Reviewer	Ensure FINRA/AML alignment	Low

5. SCOPE

In Scope:

- Analysis of 5,000 transactions: Jan-Dec 2024

- Fraud analysis by merchant category, state, hour-of-day, amount bucket, customer

- Merchant risk scorecard view (SQL CREATE VIEW)

- Excel workbook: 4-tab pivot analysis with embedded charts

- Power BI dashboard: 3 pages with interactive slicers

- Fraud rule recommendations with estimated impact

Out of Scope:

- Real-time transaction processing or live data feeds

- Machine learning model development (Phase 2)

- Integration with production payment systems

- PCI-DSS compliance certification

6. ASSUMPTIONS & CONSTRAINTS

Category	Description
Assumption	Synthetic dataset mirrors real transaction patterns for POC purposes
Assumption	Fraud labels are accurate and representative of real fraud logic
Assumption	Power BI Desktop (free) is available for dashboard development
Constraint	No access to live production database - analysis uses CSV export
Constraint	Single-analyst delivery, no development team resources
Constraint	Timeline: 2-week delivery for full analytical package

7. SUCCESS CRITERIA

KPI	Definition	Target	Measurement Method
Fraud Rate Identified	% fraudulent / total transactions	Baseline established	SQL KPI query
Category Coverage	All merchant categories risk-scored	100% coverage	Scorecard view
Dashboard Adoption	Risk team uses dashboard weekly	Active use within 30 days	Usage tracking
Rule Implementation	At least 1 rule deployed from recommendations	Within 60 days	Engineering ticket
Exposure Quantified	Total dollar exposure broken down by segment	Full breakdown delivered	Excel summary

8. DEPENDENCIES

- Transaction data export from payment processor (CSV format)

- Access to Power BI Desktop for dashboard development

- Stakeholder availability for requirements validation and BRD sign-off

- Rule-engine architecture review with Engineering before Phase 2