# π Shira: Shariah Compliance Prediction Model
> **Real-time Islamic finance compliance screening for 605 Indonesian companies using machine learning**
## π Executive Summary
This project delivers a **production-ready machine learning system** that predicts Shariah (Islamic finance) compliance for Indonesian Stock Exchange (IDX) listed companies using **real financial data (2020-2023)** from 605 companies.
### β¨ Key Achievement
Transformed the project from synthetic data to **real Indonesian financial statements** (89,243 records) and trained an XGBoost model achieving:
| Metric | Value | Status |
|--------|-------|--------|
| **Test Accuracy** | 92.00% | β
Validated |
| **ROC-AUC** | 92.83% | β
High Confidence |
| **Training Companies** | 496 | β
Real IDX Data |
| **Features Engineered** | 12 Shariah-compliant ratios | β
Domain-aligned |
| **Compliance Rate** | 22.2% compliant | β
Realistic for Indonesia |
| **Model Size** | 4.2 MB | β
Lightweight |
---
## π― Business Problem & Solution
### The Problem
- Indonesian Islamic finance requires **Shariah compliance screening** for all investments
- Manual audits are **expensive, slow, and subjective**
- Regulators need **consistent, auditable, transparent** decision-making
- Current rules-based approaches miss **nuanced financial patterns**
### The Solution
**ML-powered compliance screening** that:
- β
Analyzes 12 financial ratios per company
- β
Applies OJK/DSN-MUI Islamic finance rules
- β
Provides confidence scores and explanations
- β
Processes 605 companies in 60%) OR (Interest Income Ratio > 10%) OR ...
β Non-Compliant (FAIL)
ELSE IF (All Financial Rules Pass)
β Compliant (PASS)
ELSE
β Borderline (Manual Review)
```
---
## π Results & Insights
### Compliance Distribution
```
Total Companies Analyzed: 495
β
Shariah Compliant: 110 companies (22.2%)
β Non-Compliant: 385 companies (77.8%)
Compliance Breakdown:
βββ By Sector Compliance:
β βββ Oil & Gas: 1/5 (20.0%)
β βββ Other: β¦