Made byBobr AI

MuleNet: Identifying Suspicious Financial Mule Accounts with AI

Learn how MuleNet uses counterfactual AI, LLMs, and ensemble ML models like XGBoost to detect financial mule accounts by analyzing behavioral 'Humanity Scores'.

#fintech#fraud-detection#ai-ml#fincrime#counterfactual-ai#machine-learning#xgboost#llm
Watch
Pitch

MuleNet

AI/ML-Based Classification of Suspicious Mule Accounts

Detect the financial life that should exist — but doesn't.

FinCrime Track
AI Division
Team Delta

Powered by XGBoost · LightGBM · LLM · Counterfactual AI

Made byBobr AI
The Problem

Mule Accounts Are Hiding in Plain Sight

₹1.3T+

Lost annually to mule fraud

3 in 10

Mule accounts go undetected

48hrs

Average money transfer window

Traditional rule-based systems catch less than 40% of mule accounts

Genuine Account

Salary
Bills
ATM
Groceries

Mule Account

Bulk Inward
Rapid Outward
No lifestyle spend
Made byBobr AI

CFI

Counterfactual Fraud Investigator

Detect fraud by identifying the financial life that SHOULD exist, but doesn't.

1

Bank Data

Raw transactions & events

2

Feature Engineering

Behavioral signals

3

Persona Engine

Customer clustering

4

Counterfactual Generator

Expected baseline

5

Humanity Score

Deviation metric

Fraud ML Model

Risk probability

LLM Investigator

Contextual analysis

Analyst Dashboard

Actionable insights

Key Differentiator: CFI doesn't just score accounts — it reconstructs what a genuine financial life should look like, then measures the gap.

Made byBobr AI
MODULE 01–02

Raw Data → Intelligent Features

Feature Categories

Transaction Features

Avg amount, Median, Max/Min amount

Velocity Features

Txns/day, Inward-Outward gap, Night ratio

Diversity Features

Unique beneficiaries & senders

Stability Features

Monthly periodicity score

Input Specification

Input: F115 → F3894
Output: Target: F3924

Feature Importance

Transaction
35%
Velocity
28%
Diversity
22%
Stability
15%

3,780 Features → Engineered to ~25 High-Signal Indicators

Made byBobr AI
MODULE 02–03

Who is This Person?

Persona Engine

KMeans / GMM

Salaried

Salary · Bills · ATM · Groceries · Fuel
KMeans / GMM

Student

Recharge · Food · UPI transfers · Low balance
KMeans / GMM

Business

Suppliers · B2B transfers · Invoice payments
KMeans / GMM

Retired

Pension · Medical · Low velocity · Regular SIP

Counterfactual Generator

Salaried
80%
Student
12%
Business
5%
Retired
3%
IF Genuine (Salaried), EXPECT:
Salary
Utility Bills
Merchant Spend
ATM Withdrawals
Trained ONLY on genuine accounts (F3924=0) to learn authentic spending DNA
Made byBobr AI
MODULE 04–05

The Gap That Reveals Everything

Reality Comparison Engine

Expected Behavior
Category
Observed Reality
Salary credit monthly
INCOME
No regular income ❌
Utility bills paid
BILLS
No bills detected ❌
ATM withdrawals
CASH
No ATM usage ❌
Grocery merchants
SPEND
No retail spending ❌
Fuel transactions
MOBILITY
No fuel/travel ❌

Humanity Score Gauge

18%
POTENTIAL MULE
Normal (80-100)
Slightly Abnormal (60-80)
Suspicious (40-60)
Highly Suspicious (20-40)
⚠️ Potential Mule (<20)
Humanity Score = (Observed / Expected) × 100

A genuine human leaves financial footprints. Mules don't.

Made byBobr AI
MODULE 06

Triple-Layer ML Ensemble

XGBoost

High Precision

Gradient boosted trees, captures non-linear feature interactions

Random Forest

Low Variance

Ensemble of decision trees with bootstrapping, robust to outliers

LightGBM

Fast & Scalable

Leaf-wise tree growth, handles large feature space efficiently

Original Features (F115-F3894)

+ Engineered Features (~25) + Humanity Score

Fraud Probability Score

Confidence Score 92%

Stacked Ensemble: Meta-learner combines all three model outputs for final classification

Made byBobr AI
MODULE 07–08

From Score to Story

LLM Investigator

> INITIALIZING INVESTIGATOR QUERY...
Persona: Salaried Employee
Expected: Salary credit, Bills, ATM, Groceries, Fuel
Observed: Bulk inward transfers × 3, Immediate dispersal to 8 accounts, No lifestyle spending
Risk Score: 92% | Humanity Score: 18%
⚠️ INVESTIGATION SUMMARY: Account exhibits classic mule behavior — large inward transfers immediately dispersed to multiple beneficiaries with zero lifestyle spending. Recommend immediate freeze and SAR filing.

Analyst Dashboard — One Screen, Full Picture

Risk Score
92%
Humanity Score
18%
Selected Persona
Salaried
UUID: 8F92-4AEB
Expected Life
Salary credit
Bills
ATM
Groceries & Fuel
Observed Life
Bulk inward transfers × 3
Immediate dispersal to 8 accounts
No lifestyle spending
AI Investigation Report
Account flagged for zero retail footprint. Immediate dispersal directs funds entirely to outbound typologies. System recommends auto-freeze and SAR generation.
FREEZE ACCOUNT
Made byBobr AI
ARCHITECTURE
End-to-End System Flow
MOD. 01
Bank Transaction Dataset
MOD. 02
Feature Engineering Pipeline
MOD. 03A
Genuine Account Filter (F3924=0)
MOD. 03B
KMeans/GMM Clustering
MOD. 04
Persona Assignment Engine
MOD. 05A
Counterfactual Generator
MOD. 05B
Reality Comparison Engine
MOD. 06
Humanity Score Calculator
MOD. 07A
Fraud ML Classifier (XGBoost+RF+LGBM)
MOD. 07B
LLM Investigator (GPT-4/Gemini)
MOD. 08
Analyst Dashboard + Alert System
Made byBobr AI
OUR EDGE

Why CFI Wins the Hackathon

❌ Most Teams

Dataset
XGBoost
Fraud Score

What's missing?

  • No explainability
  • No account profiling
  • Black box prediction
  • No narrative for analyst
VS

✅ CFI

Dataset
Who is this person?
What life should exist?
What life actually exists?
Missing Humanity
Fraud Probability

What we deliver:

  • Persona-based counterfactuals
  • Explainable Humanity Score
  • LLM investigation narrative
  • Analyst-ready dashboard
Interpretable AI
Novel Counterfactual Approach
LLM Integration
End-to-End Pipeline

We don't just detect fraud. We reconstruct the truth.

Made byBobr AI

MuleNet

CFI — Counterfactual Fraud Investigator

Detect fraud by identifying the financial life that should exist, but doesn't.

8 Modules Complete Pipeline
3 ML Models Ensemble Approach
1 Goal Stop Financial Crime

Tech Stack

Python
XGBoost
LightGBM
Random Forest
KMeans
GMM
LLM/GPT
Streamlit Dashboard

Questions?

Built for Hackathon Selection 2026

Made byBobr AI
Bobr AI

DESIGNER-MADE
PRESENTATION,
GENERATED FROM
YOUR PROMPT

Create your own professional slide deck with real images, data charts, and unique design in under a minute.

Generate For Free

MuleNet: Identifying Suspicious Financial Mule Accounts with AI

Learn how MuleNet uses counterfactual AI, LLMs, and ensemble ML models like XGBoost to detect financial mule accounts by analyzing behavioral 'Humanity Scores'.

MuleNet

AI/ML-Based Classification of Suspicious Mule Accounts

Detect the financial life that should exist — but doesn't.

Powered by XGBoost · LightGBM · LLM · Counterfactual AI

FinCrime Track

AI Division

Team Delta

The Problem

Mule Accounts Are Hiding in Plain Sight

₹1.3T+

Lost annually to mule fraud

3 in 10

Mule accounts go undetected

48hrs

Average money transfer window

Traditional rule-based systems catch less than 40% of mule accounts

Genuine Account

Salary

Bills

ATM

Groceries

Mule Account

Bulk Inward

Rapid Outward

No lifestyle spend

CFI

Counterfactual Fraud Investigator

Detect fraud by identifying the financial life that SHOULD exist, but doesn't.

Bank Data

Raw transactions & events

Feature Engineering

Behavioral signals

Persona Engine

Customer clustering

Counterfactual Generator

Expected baseline

Humanity Score

Deviation metric

Fraud ML Model

Risk probability

LLM Investigator

Contextual analysis

Analyst Dashboard

Actionable insights

CFI doesn't just score accounts — it reconstructs what a genuine financial life should look like, then measures the gap.

MODULE 01–02

Raw Data → Intelligent Features

Feature Categories

Transaction Features

Avg amount, Median, Max/Min amount

Velocity Features

Txns/day, Inward-Outward gap, Night ratio

Diversity Features

Unique beneficiaries & senders

Stability Features

Monthly periodicity score

Input Specification

F115 → F3894

Target: F3924

Transaction

35%

Velocity

28%

Diversity

22%

Stability

15%

3,780 Features → Engineered to ~25 High-Signal Indicators

MODULE 02–03

Who is This Person?

Persona Engine

Salaried

Salary · Bills · ATM · Groceries · Fuel

Student

Recharge · Food · UPI transfers · Low balance

Business

Suppliers · B2B transfers · Invoice payments

Retired

Pension · Medical · Low velocity · Regular SIP

Counterfactual Generator

IF Genuine (Salaried), EXPECT:

Salary

Utility Bills

Merchant Spend

ATM Withdrawals

Trained ONLY on genuine accounts (F3924=0) to learn authentic spending DNA

The Gap That Reveals Everything

MODULE 04–05

Reality Comparison Engine

Humanity Score Gauge

Expected Behavior

Category

Observed Reality

Salary credit monthly

INCOME

No regular income ❌

Utility bills paid

BILLS

No bills detected ❌

ATM withdrawals

CASH

No ATM usage ❌

Grocery merchants

SPEND

No retail spending ❌

Fuel transactions

MOBILITY

No fuel/travel ❌

18%

POTENTIAL MULE

Normal (80-100)

Slightly Abnormal (60-80)

Suspicious (40-60)

Highly Suspicious (20-40)

⚠️ Potential Mule (<20)

Humanity Score = (Observed / Expected) × 100

A genuine human leaves financial footprints. Mules don't.

Triple-Layer ML Ensemble

MODULE 06

XGBoost

Gradient boosted trees, captures non-linear feature interactions

High Precision

Random Forest

Ensemble of decision trees with bootstrapping, robust to outliers

Low Variance

LightGBM

Leaf-wise tree growth, handles large feature space efficiently

Fast & Scalable

Original Features (F115-F3894)

Engineered Features (~25)

Humanity Score

Fraud Probability Score

Stacked Ensemble: Meta-learner combines all three model outputs for final classification

MODULE 07–08

From Score to Story

LLM Investigator

Salaried Employee

Salary credit, Bills, ATM, Groceries, Fuel

Bulk inward transfers × 3, Immediate dispersal to 8 accounts, No lifestyle spending

Risk Score: 92% | Humanity Score: 18%

⚠️ INVESTIGATION SUMMARY: Account exhibits classic mule behavior — large inward transfers immediately dispersed to multiple beneficiaries with zero lifestyle spending. Recommend immediate freeze and SAR filing.

Analyst Dashboard — One Screen, Full Picture

92%

18%

Salaried

Expected Life

Observed Life

AI Investigation Report

Account flagged for zero retail footprint. Immediate dispersal directs funds entirely to outbound typologies. System recommends auto-freeze and SAR generation.

FREEZE ACCOUNT

ARCHITECTURE

End-to-End System Flow

Bank Transaction Dataset

Feature Engineering Pipeline

Genuine Account Filter (F3924=0)

KMeans/GMM Clustering

Persona Assignment Engine

Counterfactual Generator

Reality Comparison Engine

Humanity Score Calculator

Fraud ML Classifier (XGBoost+RF+LGBM)

LLM Investigator (GPT-4/Gemini)

Analyst Dashboard + Alert System

OUR EDGE

Why CFI Wins the Hackathon

Most Teams

Dataset

XGBoost

Fraud Score

What's missing?

No explainability

No account profiling

Black box prediction

No narrative for analyst

CFI

Dataset

Who is this person?

What life should exist?

What life actually exists?

Missing Humanity

Fraud Probability

What we deliver:

Persona-based counterfactuals

Explainable Humanity Score

LLM investigation narrative

Analyst-ready dashboard

Interpretable AI

Novel Counterfactual Approach

LLM Integration

End-to-End Pipeline

We don't just detect fraud. We reconstruct the truth.

MuleNet

CFI — Counterfactual Fraud Investigator

Detect fraud by identifying the financial life that should exist, but doesn't.

8 Modules

Complete Pipeline

3 ML Models

Ensemble Approach

1 Goal

Stop Financial Crime

Tech Stack

Python

XGBoost

LightGBM

Random Forest

KMeans

GMM

LLM/GPT

Streamlit Dashboard

Questions?

Built for Hackathon Selection 2026