Credit, where the
data does not yet
look the way the
textbook expects.
Across most of Africa, an SMB's full financial life does not appear on a bank statement. It happens in mobile money, in supplier ledgers, in informal cash patterns. Traditional underwriting reads the formal account and rejects what it cannot measure.
Mansa builds the underwriting layer that reads everything else. African banks and microfinance institutions use our products to score, instruct, and monitor SMB loans against the data that actually describes the borrower — not the data that happens to be the easiest to find.
What we mean when we say credit intelligence.
The textbook of SMB credit was written for markets with bureaus, formal employment, and bank statements that capture most of a borrower's economic life. In sub-Saharan Africa, that textbook describes perhaps fifteen percent of the data we need to read.
The other eighty-five percent is real, and it is recorded — just not in the systems banks were built to query. Mobile money flows. Supplier invoices. Cooperative ledgers. Behavioural patterns at the wallet level.
Mansa treats alternative data not as a clever supplement to traditional underwriting, but as the primary signal in markets where that's what the data actually says. Our models are built to be calibrated, auditable, and defensible to a regulator — because the institutions we serve cannot afford anything less.
Two products. One pipeline.
Castel handles the loan from application to disbursement. Almami takes over once the loan is on the books — monitoring repayment, surfacing early signals, and managing the portfolio through to maturity.
From application intake to the analyst's final decision, on a single platform. Instant pre-scoring, document collection, AI-led instruction, scoring, and committee review — every step traceable and explainable.
- Multi-signal scoring built for African data
- Custom models trained on your customer data
- Branded public application portal in EN, FR, AR, Wolof
- Full audit trail and feature attribution per decision
- Configurable loan products and decision rules
The watchful second half. Once the loan is booked, Almami monitors repayment behaviour, surfaces early warning signals, and triggers interventions before a loan turns non-performing. Currently in development, available for design partners.
- Systematic credit portfolio management
- Core banking integration with external data sources
- Behavioural signal monitoring after disbursement
- Automated reporting aligned with international standards
How an underwriting decision is made.
Every Mansa decision passes through four steps. Each one is logged. Each one is auditable. The model never decides alone — it produces a probability, and a risk officer reads it.
Application
Submitted through a branded public form your bank operates under its own identity. Available in EN, FR, AR, and Wolof. KYC, document upload and consent capture happen here — the applicant never sees Mansa.
Ingestion
Castel ingests data from external providers that describe the applicant: bank statements, mobile money operators, supplier records, BCEAO RCCM. Inputs are normalised, deduplicated, and timestamped against a single ledger.
Scoring
A model tailored to your portfolio produces a calibrated probability of default. Each output is accompanied by feature attribution — which signals contributed how much, in plain language and as numerical weights. The score is not a verdict.
Decision
A risk officer reviews. They approve, decline, or override. Every override is logged with a reason, and feeds back into model evaluation. Regulators receive a complete audit trail per decision, on request.
If you underwrite SMB credit on the continent, we'd like to meet you.
A focused walkthrough with your risk team, on a few representative dossiers from your loan book. We'd like to understand how you decide today, and show how Castel could fit into that.