Scoring layers
How the rules are organised into a top-to-bottom decision pipeline.
Scoring layers
Rules are grouped into layers that run top to bottom — a knockout stops the file before it reaches scoring. In the engine UI the layers are numbered sequentially over the layers that actually have rules, so there is never a confusing gap.
| Layer | What it does |
|---|---|
| Fraud & integrity | Document tampering, name-mismatch and mule checks. A hit sends the file to manual review. |
| Credit knockouts | Bureau red-flags and score floors that stop a file before scoring. |
| Scorecard & scenarios | The points each signal adds or removes — this builds the credit score. |
| Affordability & offer | Caps the EMI and loan amount the income and balances can support (FOIR, ABB cover). |
| AI review | The AI reads the statement for anomalies and advises; it never sets the number. |
Eligibility (not shipped by default)
An "Eligibility" layer — minimum age, income floor, employment type, geography — is intentionally empty by default: an age or income cut-off that shipped on would reject real applicants no lender chose to exclude. Eligibility is per-lender; the variables exist (age/gender/employment are derived from the bureau and the statement) so you can add the rules you need.