Pure NumPy gradient-like risk scoring engine calibrated against Basel III benchmarks.
R² = 0.8955 on 15 Basel III operational anchors.
Each profile uses framework-specific feature weights derived from EBA supervisory convergence data:
1git clone https://github.com/Alvoradozerouno/GENESIS-v10.1.git
2cd GENESIS-v10.1
3pip install -r requirements.txt
4uvicorn genesis_api:app --port 8080
5# Default dev key: genesis-dev-key
6# Production: export GENESIS_API_KEY=<your-secure-key>
1curl -X POST http://localhost:8080/api/risk/score \
2 -H "X-API-Key: genesis-dev-key" \
3 -H "Content-Type: application/json" \
4 -d '{
5 "cpu": 85,
6 "memory": 70,
7 "disk_usage": 60,
8 "network_io": 50,
9 "error_rate": 15,
10 "framework": "dora"
11 }'
1curl http://localhost:8080/metrics
2# genesis_model_r2 0.8955
3# genesis_audit_entries_total 42
4# genesis_up 1
1{
2 "risk_score": 62.3,
3 "risk_level": "HIGH",
4 "framework": "dora",
5 "model_confidence_r2": 0.8955,
6 "feature_importance": {"cpu": 0.2, "memory": 0.12, "network_io": 0.25, "disk_usage": 0.08, "error_rate": 0.35},
7 "regulatory_action": "Board notification + corrective action within 24h",
8 "audit_ref": "2026-01-14T10:00:00+00:00"
9}
