Family
Rule-based + XGBoost calibration
in-developmentApache 2.0tabularboth
Financial Health Score.
Composite financial wellness score (0-100) — rule-based sub-scores + XGBoost calibration
Foundation · Rule-based + XGBoost calibration
What it does
The honest description.
Composite financial wellness score (0-100) — rule-based sub-scores + XGBoost calibration
Architecture
How it works.
Rule-based sub-scores aggregated from user financial state: emergency fund, debt ratio, savings rate, income stability, investment diversification, expense control. Composite 0-100 wellness score. A deterministic 6-dimension weighted-composite formula currently serves; the XGBoost-calibration phase that maps sub-scores to a stress-inverse scale is the intended target, not yet served.
Training data & drift
What it learned from, and how we watch it.
Source
Inputs: Rule-based sub-scores aggregated from user financial state: emergency fund, debt ratio, savings rate, income stability, investment diversification, expense control.
Drift baseline · current quarter
Drift baseline not yet documented for this model.
What it's NOT
- Two-phase scoring (rules → XGBoost calibration).
- Self-healing enabled (D4 absorbed legacy 'health_score' alias).
Who calls this model
Across the house and the API.
Internal routes
No public routes documented yet.
Featured in
/features/health-scoreVersion history · immutable once published
Every release, traceable.
Data Mukodi holds about you is subject to DPDP §12 erasure (use /consent in the app), and any concern about this model can be raised via [email protected] under DPDP §13 grievance, or via /security.