GST Tax Evasion Network Mapping

GST Intelligence uncovered a network of 400 shell companies generating fake ITC claims worth Rs. 900 crores. Students will map complex networks and analyze financial flows.

# Aplly.xyz Case Study Submission

## Title
GST Tax Evasion Network Mapping

## Type
Fraud Pattern Analysis

## Difficulty
Intermediate

## Estimated Time
60 minutes

## Overview
GST Intelligence uncovered a network of 400 shell companies generating fake ITC claims worth Rs. 900 crores. Students will map complex networks and analyze financial flows.

## Case Details

Function Focus: Fraud Pattern Analysis — manual reasoning, decomposition, and critical judgment (no spreadsheet or AI tool permitted in Phase 1)

Scenario:
You are the analyst at a fictional consultancy ("Praxis Advisors") tasked with answering: GST Tax Evasion Network Mapping. You have a clean, synthetic dataset described below. You must produce a defensible answer using structured reasoning — no tool-assisted shortcut on the first pass.

Dataset Structure:
- firm_id
- gstin
- registration_state
- filing_regularity_pct
- input_tax_claimed_lakhs
- output_tax_paid_lakhs
- itc_ratio
- turnover_declared_cr
- industry
- related_firms
- e_waybill_mismatches
- director_common_count
- fraud_score
- flagged

Tasks:
1. Profile the distribution of key numeric columns; identify outliers, tail values, or groups that look systematically different.
2. Flag candidate fraudulent records by rule-of-thumb thresholds you define yourself. Write the rules down before applying them.
3. Look for coordinated patterns (shared attributes, networks, repetition) that single-record checks would miss.
4. Estimate the financial exposure of the flagged set and state your confidence and the biggest assumption.
5. Only after the manual pass, compare your flags against an automated model/threshold and explain the gaps.

Expected Output:
A one-page fraud assessment memo: flagged record list with rules, network/pattern evidence, exposure estimate, confidence statement.

Evaluation Criteria:
Correctness of threshold rules, detection of coordinated patterns, accuracy of exposure estimate, honest confidence statement.

## Data Sources

| firm_id | gstin | registration_state | filing_regularity_pct | input_tax_claimed_lakhs | output_tax_paid_lakhs | itc_ratio | turnover_declared_cr | industry | related_firms | e_waybill_mismatches | director_common_count | fraud_score | flagged |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| F001 | 27AABCP1234Q1Z2 | Maharashtra | 82 | 85 | 72 | 1.18 | 2.5 | Electronics | 0 | 2 | 0 | 18 | False |
| F002 | 07AABCK5678R1Z3 | Delhi | 35 | 220 | 15 | 14.67 | 0.5 | Iron/Steel | 8 | 45 | 4 | 92 | True |
| F003 | 33AAECL9012T1Z4 | Tamil Nadu | 90 | 150 | 145 | 1.03 | 5.8 | Automobile | 1 | 1 | 0 | 12 | False |
| F004 | 24AAFP3456U1Z5 | Gujarat | 25 | 380 | 8 | 47.5 | 0.2 | Chemicals | 12 | 68 | 3 | 98 | True |
| F005 | 29AAEQ7890V1Z6 | Karnataka | 75 | 95 | 80 | 1.19 | 3.2 | IT Services | 0 | 0 | 1 | 15 | False |
| F006 | 06AAER1234W1Z7 | Haryana | 20 | 450 | 5 | 90 | 0.1 | Textiles | 15 | 82 | 5 | 99 | True |
| F007 | 36AAES5678X1Z8 | Telangana | 85 | 180 | 165 | 1.09 | 6.1 | Pharma | 2 | 3 | 0 | 20 | False |
| F008 | 23AAET9012Y1Z9 | Madhya Pradesh | 15 | 520 | 3 | 173.33 | 0.05 | Scrap | 20 | 95 | 6 | 100 | True |
| F009 | 27AAEU3456Z1A1 | Maharashtra | 78 | 210 | 190 | 1.11 | 7.5 | FMCG | 1 | 1 | 0 | 22 | False |
| F010 | 09AAEV7890A1B2 | Uttar Pradesh | 22 | 280 | 12 | 23.33 | 0.3 | Plastic | 10 | 55 | 4 | 95 | True |


Full dataset: https://github.com/arora200/aplly_case_db/datasets/066-fraud-gst-evasion (synthetic, 15 records)

## Solution Frameworks
Pattern & anomaly detection, network/graph analysis, risk scoring, layered defense review, distribution/tail analysis

## Solver Guidance & Tutorials
_Solver guidance added by the pipeline (tutorial links) — see `solver_guidance` field._

## What You'll Learn
- Spot outliers and coordinated patterns by hand
- Write and test your own detection rules
- Estimate financial exposure honestly

## Tags
Tax Evasion, Financial Fraud, Network Analysis, Corporate Crime

## Registration Links
Register as Solver / Register as Evaluator