AfriScore
AfriScore is a B2B credit-scoring engine that converts mobile money, airtime, and utility data into explainable credit scores for lenders serving borrowers with thin or no formal credit files. The platform returns a score, risk tier, and probability of default in under a second, with feature-level reasons for each decision. It can be deployed on-premise via Docker to meet data residency requirements.
- Financial Technology
- Artificial Intelligence
- Data & Analytics
- Software Only
Funding
Founders
Founder details are not available yet.
Product
Problem
Traditional credit bureaus cover less than 5% of the population in most Sub-Saharan African countries, leaving hundreds of millions of creditworthy adults and small businesses without formal financial histories. This credit-invisible population is locked out of formal lending despite an estimated $100 billion annual credit gap, not because they are risky, but because they lack the traditional data required to prove creditworthiness.
Solution
AfriScore provides a B2B credit decisioning layer that transforms mobile money transaction histories, airtime purchase patterns, and device metadata into explainable, compliant credit decisions. The platform ingests alternative data via secure API, scores applicants using a calibrated machine-learning model, and returns a credit score, risk tier, and probability of default in under a second. Every score includes feature-level reasons and what a borrower could change, ensuring auditable and regulator-friendly outcomes. The system is designed for on-premise deployment with Docker to meet strict data residency requirements common among African financial institutions, and it never lends or holds risk—approval, limit, and pricing stay with the lender.
Target Audience
Primary customers are financial institutions across emerging African markets, including banks, microfinance institutions, digital lenders, credit unions, and BNPL providers serving borrowers with thin or no formal credit files in regions such as the CEMAC area, East Africa, and UEMOA.
Features
- Python-based ML pipeline using a calibrated Random Forest ensemble model with isotonic calibration and SHAP explainability
- Real-time scoring engine that processes mobile money, utility payments, airtime behavior, and device metadata via secure API
- SHAP-based feature contributions and counterfactual explanations for every credit decision, supporting regulatory compliance
- Self-hostable architecture supporting on-premise deployment with Docker for data residency compliance
- Live interactive demo allowing users to run hypothetical credit assessments with adjustable applicant parameters
- API reference and documentation for institutional integration