Payment Data Models
Predicting settlement outcomes before funds clear — using open banking data and behavioural analysis.
PayCo's challenge was to approve fast, low-cost payments while reducing the chance of a transaction failing later when cleared through the Bulk Electronic Clearing System (BECS). The solution combined real-time account data, transaction history, and risk scoring.
The data anatomy model builds the trusted data foundation, and the clearance risk model uses that foundation to predict payment success.
Clearance Risk
Stop valid transactions from failing because the customer's balance changes before settlement.
The Problem
A transaction approved now may fail later if the customer's balance is debited before settlement (3h45 to 111h00 window).
Settlement Windows
| Win | Mon–Thu | Fri–Mon | PH | 3-Day | 4-Day |
|---|---|---|---|---|---|
| 1 | — | — | 5h30 | — | — |
| 2 | — | — | 4h00 | — | — |
| 3 | — | — | 3h45 | — | — |
| 4 | 15h | 63h | 39h | 87h | 111h |
Transaction Flow vs. Declined Risk
Expected Balance
Formula
Expected Balance =
Current Balance
− Pending Payments
+ Expected Receipts
− Expected Spending
± Risk Buffer
Processing Flow
Payment Request
Customer initiates transaction.
Balance Check
Live balance via API.
Pending Payments
Sum in-flight transactions.
Expected Receipts
Estimate incoming credits.
Expected Spending
Forecast remaining spend.
Risk Modifiers
Adjust for unusual behaviour.
Decision Engine
Approve, divert, or block.
Three Risk Layers
Decision Outcomes
✅ Allow via BECS
Expected balance covers payment
⚡ Route to RTP
Payment is risky but valid
🚫 Block
Expected balance too low
Data Anatomy
Turning raw open banking APIs into structured data for risk models.
The Problem
Open banking APIs provide data in varying structures across banks. The challenge was mapping raw responses into a consistent, queryable database design.
Processing Flow
API Ingestion
Pull account, transaction, balance data.
Normalisation
Standardise fields into internal format.
Storage
Store in structured tables.
Aggregation
Build windows, balances, metrics.
Quality Audit
Detect anomalies across banks.
Analytics Output
Decision-ready datasets.
Dynamic Customer Data
Potential reporting metrics
Static Data
Account creation date, product type, ownership, customer identity. Determines baseline trust.
Dynamic Data
Transaction frequency, balance trends, recurring payments, merchant relationships. Changes risk profile over time.
Anomalies & Caveats
Banks vary in field population — execution datetime, merchant name, payee data. Production needs robust anomaly lists and bank-by-bank validation.
Platform Architecture
End-to-end data flow and decisioning.
End-to-End Flow
Layer 1 — Data Sources
Layer 2 — Data Anatomy Model
Transforms raw API responses into a consistent, queryable data platform.
Canonical Tables
- accounts
- customers
- transactionhistory
- directdebits
Feature Tables
- accountbalances
- transactionwindows
- scheduledpayments
- payees
Data Quality
- Anomaly detection
- Bank-by-bank validation
- Fallback logic
- Field consistency audit
Layer 3 — Clearance Risk Model
Predicts balance sufficiency at settlement time using expected balance calculations.
Risk Layers
- Expected payments model
- Unexpected payments model
- Manipulation detection
Calculations
- Current balance
- + Expected inflows
- − Known outflows
- − Risk buffer
Scoring
- Balance sufficiency check
- Settlement window timing
- Behavioural trust signals
- Historical default rate
Layer 4 — Payment Decision
✅ Allow via BECS
Expected balance covers payment
⚡ Route to RTP
Payment is risky but valid
🚫 Block
Expected balance too low
Layer 5 — Operational Infrastructure
Settlement outcomes are recorded and fed back into the model to continuously improve accuracy.
Monitoring
- Settlement success/failure tracking
- Default rate by settlement window
- Model accuracy over time
Optimisation
- Risk buffer calibration
- Threshold tuning per merchant
- Seasonal pattern adjustment
Assumptions, Limitations & Next Steps
Case study prepared for PayCo — a risk-aware payment platform built on open banking infrastructure.