The credit signal the bureau doesn't have.
Behavioural credit scoring for South African lenders
Millions of creditworthy South Africans get a reflexive "no": not because they can't repay, but because the credit bureau has nothing on them. Affy reads their bank statement instead, and turns three months of real cash behaviour into the confidence to say yes.
Turning the six major SA bank statements into a credit signal
Most declines aren't bad credit.
They're no credit.
Credit invisible
But most "thin file" people have jobs, homes and a long history of meeting their obligations. They simply never left a trail the bureau can read.
Untapped market
South Africans could be accurately scored today, with the right data. They have jobs, pay rent, meet obligations. The bureau just can't see it.
Manual grind
per application reading statements, categorising transactions, plugging numbers into spreadsheets. Qualified staff doing work a machine should do.
* Source: TransUnion SA, CreditVision Link, credit-invisible consumer estimates.
It replaces the slow, blind parts of your credit decision.
For thin-file applicants the bureau comes back empty, so today the file lands on an analyst's desk, or gets declined unseen.
Today, on a thin-file applicant
- A bureau enquiry that returns no usable score. Paid for, learned nothing
- 15–45 minutes of an analyst reading the statement by hand. Slow and inconsistent
- Or a decline unseen. A good customer lost, with no audit trail of why
With AffyScore
- A score in minutes, automatically, from the statement they already sent
- Consistent and auditable: every output versioned for review and dispute
- More good customers approved, more bad ones caught, on evidence
Bank statements in. Decision pack out.
Three months of statements. Six stages. One complete, defensible credit decision.
Intake
Operator upload, customer self-upload via tokenised link, or direct API call. Batch up to 30 statements.
Extract
Six SA banks parsed by fingerprint: FNB, Standard Bank, ABSA, Nedbank, Capitec, Discovery. Regex extraction with AI vision fallback for scanned or image-based documents.
Tamper Check
Document tampering checks across metadata, font/layout, mathematical, and sequence anomalies. Advisory: flags findings for the human, never auto-declines.
Transaction Categorisation
Every transaction sorted into NCR expense categories over a 3-month window. Counterparty identified. Salary detected by recurrence. Discretionary spend flagged. Net available income derived.
Affordability
Reg 23A affordability on statement-derived income. Disposable income, maximum instalment, norm-floored expenses, audit-stamped output.
Score + Recommendation
300–850 behavioural score across four weighted families. Reason codes in plain English. Outcome recommendation to support the lender's decision.
Collect on the right day.
For debit-order lenders, the real question isn't just "can they afford it" — it's "will the debit actually fire, and when." Affy answers both.
What this means for a debit-order lender
Affordability says they can pay. The collection forecast says when the money is actually there, and whether your debit order will clear.
A debit order set on the wrong day bounces even for good borrowers. The right day cuts returned debits and the cost that comes with them.
Salary lands, debit orders pull, balance decays. The forecast reads that pattern across 3 months and recommends the day with the highest chance of clearing.
Every bounced debit costs: re-presentation fees, broken arrangements, provisioning. Collecting on the right day reduces all three.
Line-by-line. Every transaction. Fully categorised.
Download sample output from a real extraction. Every transaction is there: date, description, amount, balance, category, confidence score, and counterparty.
Four families. One number. Every factor traceable.
300–850, built from what the statement actually shows. Not a black box; every point traces back to a transaction.
Income
- Salary recurrence
- Salary stability (CoV)
- Irregular-income share
Cash Buffer
- Average daily balance between pay cycles
- Low-balance days
Discipline
- Returned debit orders
- Lender stacking
- Debt-service ratio
Red Flags
- Gambling share-of-wallet
- Cash withdrawal dominance
Less room before a new instalment overcommits the applicant.
REASON 02 Gambling is 5-10% of income.
Material gambling erodes real affordability.
Every score ships with plain-English reason codes. Your underwriter sees why, not just what.
The same data reveals product fit.
Underwriter-facing signals. No automated marketing. The human decides.
Plugs into your workflow. Not the other way around.
⚡ API
- REST API with async webhooks
- Fire-and-forget: POST statements, get job ID, receive result via callback
- Batch processing: overnight cron, morning review queue
- n8n, Zapier, or direct HTTP integration
- JSON response with full decision pack
🖥 Portal
- Web dashboard for manual upload and review
- Operator uploads statements, views pipeline progress
- Score card, reason codes, affordability output, tamper advisory
- Export to JSON, CSV, PDF, or Excel
Built for a regulated lending book.
Transparent, tunable, and yours to integrate.
Transparent pricing. Per extraction.
Prepaid bundles in Rands. No minimum contract. Top up credits as you go.
Book a demo and we'll set you up with free credits for your first proof of concept.
What it costs, in context
Per thin-file applicant. Unlike the bureau, you get a usable answer.
Run it on your own statements.
Book a 15-minute demo. Bring 3 months of bank statements. We run them live and walk you through the full decision pack.