From a phone’s transaction history to a lending decision
AfriScore reads the digital footprints your borrowers already leave and hands you a score with reasons. You keep the decision.
Four steps, one API call
- 1
Data comes in
Mobile money summaries, utility payments, airtime patterns and device metadata arrive through a secure API. No bureau file needed.
- 2
The engine scores
A calibrated machine-learning model returns a credit score, a risk tier and a probability of default, well under a second.
- 3
Reasons are attached
Every score lists the factors that moved it, and what a borrower could change to improve it.
- 4
The lender decides
Approval, limit and pricing stay with your policy. AfriScore never lends and never holds the risk.
You keep the decision
AfriScore
- A credit score
- A risk tier
- A probability of default
- Reasons for every score
You
- Approval
- Limit
- Pricing
- The loan and the risk
How a pilot runs
Integration
AfriScore connects to your loan origination system by API or a light adapter.
Shadow mode
Every application is scored in parallel. Results are logged and never influence your decision.
Calibration
Real outcomes (approvals, rejections, repayments) tune the engine to your customers.
Report
You get a statistical analysis of how it would have performed on your portfolio, with a clear go or no-go.
How AfriScore earns
Pay per score
From $0.25
per scoring request, through the API. Billed in your local currency.
- Score, risk tier and probability of default
- Reasons with every score
Enterprise subscription
For lenders scoring at volume: a monthly commitment with lower per-score rates as your volume grows. Terms are agreed with you.
Talk to usOn the roadmap
See it on your own portfolio
The pilot is free and runs beside your current process.
Apply for the pilot