Skip to content
Guides

Credit decisions, under governance

Governance, policy versioning, decision traceability, model risk and security. Reference material for banks and lenders that need to automate without losing control.

Risk
Controlled experimentation

Champion / Challenger: testing a new credit policy without risking the portfolio

How to evaluate a new credit policy against the one already in production, measuring its real impact on a slice of live traffic before you adopt it.

Read the guide5 min
Model risk

Model risk management: governing scoring and ML models in credit decisions

Scoring and ML models sharpen credit decisions but add model risk: bias, drift, weak explainability. Govern them with validation, monitoring and audit trails.

Read the guide6 min
Risk matrices

From Excel matrix to decision engine: how to digitize credit risk matrices

How to move the risk matrices living in Excel into a decision engine: versioned, testable, auditable lookup tables your risk team edits without writing code.

Read the guide5 min
Bulk processing

Batch credit evaluation: portfolio re-scoring and pre-approval campaigns

Run the same credit policy across thousands of customers at once: pre-approval campaigns, portfolio re-scoring and backtesting, with no engineering project.

Read the guide6 min
Models in production

Your scoring model in production: from notebook to decision, without rewriting it

How to take your own machine learning model into a live credit policy: Python model upload, versioning, execution as a flow node and custom logic.

Read the guide6 min
Bias and inclusion

Bias in credit scoring: govern it to expand credit, not to shrink it

Scoring models inherit the bias in their data. How to detect it with segment monitoring, mitigate it in the policy and make inclusion a portfolio advantage.

Read the guide6 min
Collections

Collections decisioning: prioritizing early-stage delinquency with the engine

The same engine that originates can decide collections: who to work first, on which channel, with which offer. Automate early delinquency with re-scoring.

Read the guide6 min
Credit limits

Dynamic credit limit management: lines that grow (and shrink) with the evidence

A credit limit should not be frozen at origination. How to automate line increases and decreases with rules, periodic re-scoring and governance.

Read the guide5 min
Risk-based pricing

Risk-based pricing: the interest rate as a decision, not a fixed table

Charging everyone the same rate makes good borrowers subsidize bad ones. How to run risk-based pricing with rate matrices, hard caps and testing.

Read the guide5 min
Fraud

How to build an anti-fraud flow in a decision engine

The engine doesn't detect the deepfake: it orchestrates your identity, anti-fraud and bureau providers, crosses their signals with your rules and decides approve, reject or refer to review.

Read the guide8 min
Risk

Low and Grow: lending to thin-file customers by starting small

What the Low and Grow strategy is: approve small amounts for customers with no credit history, read payment behavior and grow limits gradually and safely.

Read the guide9 min
Risk

Model reproducibility: the same result in your notebook and in production

How to ensure a scoring model returns the same result in production as in your local environment: pinned environment, declared data contract and validation with tolerance.

Read the guide8 min

Would this work for your decisioning process?

We review how you decide today and show you how it would work in the engine, with your own sources and policies.