Insurance Claim Fraud Detection

A health insurance company noticed unusual patterns in 5,000 cashless claims worth Rs. 50 crores from 50 hospitals. Students will identify statistical outliers and develop fraud scoring systems.

# Aplly.xyz Case Study Submission

## Title
Insurance Claim Fraud Detection

## Type
Fraud Pattern Analysis

## Difficulty
Intermediate

## Estimated Time
60 minutes

## Overview
A health insurance company noticed unusual patterns in 5,000 cashless claims worth Rs. 50 crores from 50 hospitals. Students will identify statistical outliers and develop fraud scoring systems.

## 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: Insurance Claim Fraud Detection. 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:
- claim_id
- policy_type
- claim_amount_rs
- policy_holder_age
- policy_tenure_months
- claim_reason
- accident_location
- witness_available
- police_report_filed
- medical_reports_count
- claim_history_count
- discrepancy_count
- fraud_score
- investigation_required
- fraud_confirmed

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

| claim_id | policy_type | claim_amount_rs | policy_holder_age | policy_tenure_months | claim_reason | accident_location | witness_available | police_report_filed | medical_reports_count | claim_history_count | discrepancy_count | fraud_score | investigation_required | fraud_confirmed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CL001 | Health | 250000 | 45 | 24 | Hospitalization | Mumbai | True | True | 5 | 2 | 0 | 12 | False | False |
| CL002 | Motor | 180000 | 32 | 6 | Accident | Highway NH-8 | False | False | 1 | 0 | 4 | 85 | True | True |
| CL003 | Life | 5000000 | 55 | 120 | Natural death | Home | True | True | 2 | 3 | 1 | 15 | False | False |
| CL004 | Health | 85000 | 28 | 3 | Dengue | Delhi | True | True | 8 | 1 | 0 | 8 | False | False |
| CL005 | Motor | 450000 | 38 | 1 | Theft | Parking lot | False | True | 0 | 0 | 6 | 92 | True | True |
| CL006 | Health | 320000 | 62 | 48 | Heart surgery | Chennai | True | True | 12 | 4 | 1 | 20 | False | False |
| CL007 | Motor | 220000 | 25 | 2 | Accident | City road | False | False | 2 | 0 | 5 | 78 | True | True |
| CL008 | Life | 2000000 | 42 | 36 | Accidental death | Factory | True | True | 3 | 1 | 0 | 10 | False | False |
| CL009 | Motor | 150000 | 29 | 4 | Fire damage | Parking | False | False | 1 | 0 | 7 | 95 | True | True |
| CL010 | Health | 125000 | 35 | 8 | Fracture | Sports ground | True | True | 4 | 1 | 0 | 5 | False | False |


Full dataset: https://github.com/arora200/aplly_case_db/datasets/069-fraud-insurance-claim (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
Insurance Fraud, Healthcare Fraud, Statistical Analysis, Pattern Recognition

## Registration Links
Register as Solver / Register as Evaluator