Prepayment and non-maturing deposit models for IRRBB, NII and liquidity, estimated from your customers' observed behaviour.
Retail and wholesale, transactional and savings, by product features.
Split balances into stable and volatile parts and estimate core runoff.
Estimate deposit betas and lags as market rates move up and down.
Model refinancing incentive, seasoning and burnout on mortgage books.
| Data | Needed | If missing or incomplete |
|---|---|---|
| Balance history per account | Required | Aggregate balances by product |
| Client and market rate history | Required | — |
| Prepayment events | Required (mortgages) | Industry curves, with added conservatism |
| Product features | Helpful | Product-level segmentation only |
Each comes with a recommended option, the reason and any data gap. The model owner approves the set at the design gate.
Shown next to each result. A test outside its threshold stays visible and becomes a limitation in the documentation.
| Test | Group | Threshold |
|---|---|---|
| Back-testing of runoff | Back-testing | ≤ 5% of months breach the stable share |
| Regulatory caps on repricing maturity | Regulatory | Core share and average maturity within the caps |
| Sensitivity to rate shocks | Sensitivity | Reported |
| Stability across rate regimes | Stability | Rising and falling betas within 0.3 |
| Back-testing of prepayment | Back-testing | Largest yearly CPR gap ≤ 3 points |
| Prepayment under rate shocks | Sensitivity | Reported |
| Comparison with challenger models | Challenger | Model beats a constant historical CPR |
We'll walk through your use case and show the product on data structured like yours.