Why AI Product Recommendations in Banking Have to Explain Themselves First
TL;DR Most conversations about AI in banking marketing use “next best offer,” “next best action,” and “product recommendation” as if they were interchangeable. They aren’t. A recommendation engine answers one question: which product should this customer see next. A next-best-action system answers a bigger one: whether to act at all, through which channel, at what […]
Why Customer Churn Prediction in Retail Banking Starts With the Customers Who Never Leave
TL;DR Ask a retail bank how many customers it lost last quarter, and most will pull up a report of closed accounts. That number is real. It is also increasingly beside the point. J.D. Power’s 2026 U.S. Retail Banking Satisfaction Study found that 20% of retail bank customers moved money away from their primary bank […]
Model Risk Management Services: What You’re Actually Buying
TL;DR A bank buys a model risk management assessment from a consulting firm, gets a report with a scorecard and a set of recommendations, and six months later ships three new models with none of that report’s process attached to them. The engagement ended. The obligation didn’t. Model risk management services can mean several different […]
Building a Churn Prediction Model Starts With the Label
TL;DR A propensity model’s build sequence applies to churn prediction the same way it applies to credit or growth models: source the data, engineer features, validate, then deploy. What changes for churn is the label itself, the features that actually carry signal, and the imbalance that sits underneath the data before a single model gets […]
The Model Risk Governance Structure Most Institutions Only Have on Paper
TL;DR A model risk governance chart looks the same whether the structure behind it works or not: a board, a risk management committee, a senior management function, each with a box and a reporting line. What separates a functioning structure from a decorative one shows up only when someone asks what the committee actually reviewed […]
What is Model Monitoring and why does it matter?
TL;DR A model that has stopped being right doesn’t stop predicting. It just keeps going and delivering wrong output. How do you know when a model stops being right? A model that stops being reliable does not throw an error or fail a build. It keeps running and keeps producing confident-looking outputs that are quietly […]
AI Model Monitoring for Regulated Lenders
TL;DR Most teams that say they monitor their models are watching one number: is accuracy still where it should be. That’s a real signal, and it’s also a small fraction of what a lender that has to answer to an examiner actually needs to be watching. A Dashboard That Tracks Accuracy Is Not a Monitoring […]
Model Risk: The Four Places It Enters a Lending Book
TL;DR A lending model is a simplified picture of a borrower. It takes a handful of measurable things and turns them into a number that stands in for a decision no one has time to make by hand. That works right up until the picture stops matching the borrower. Model risk is the cost of […]
What Is Model Drift?
TL;DR A model doesn’t need a bug to stop working. It just needs the world to change underneath it. Model Drift Is a Performance Problem, Not a Code Problem Model drift is the general decline in a machine learning model’s predictive performance that happens over time, as the data it scores or the relationships in […]
Model Drift: Catching Decay Before It Reaches the Regulator
TL;DR Nobody edited the code. Nobody touched the weights. Nothing broke in the way a system usually breaks. And the same model, running the same math on today’s applicants, is getting more of them wrong than it did at launch. That is drift, and it is the quietest way a working model stops working. This […]
