All Posts

What Exactly Is a Leaky Variable? A leaky variable is any feature in your training data that contains information you won't have at decision time. The most extreme example would be using default status to predict default. That creates a perfect model in development with zero real-world utility, as the model will simply learn to predict the outcome with itself. Of course, any serious data scientist would catch an error that massive. But leakage can be subtle: Post-application

Running tests has technically never been easier. With highly configurable back-end tech and sophisticated data analysis tools widely available, even early-stage lenders with small teams can run a sophisticated testing program. The ease is a double-edged sword though, as it's also become easy to drown your insights in noise with sloppy testing. To make sure testing brings meaningful results, follow these four principles. 1. You need a learning agenda. And a budget, too. There

We see so many lenders get stuck in the same paradoxical situation: they're trying to expand their reach to the millions of underbanked or thin-file customers, but their own policies stand in the way. For good reason. Governance structures designed for lending to prime, salaried borrowers shouldn't be recklessly expanded to serve borrowers with no credit history. That would be trying to serve a  motorbike mechanic using the same credit policies built for a  mid-career engine

The Short Answer: Yes, and Don't Cut Corners When investors, debt providers, and sponsor banks ask to see your credit policy, it may seem like just another box to check. Can’t we just explain the model and include some example flows? Can I whip one up with some help from ChatGPT and a few templates? But while it might seem like a boring document, the credit policy is a terrible place to skimp. Those dozens of pages prove that you're a serious lending business ready to lend re

Gradient Boost Models (GBMs) have become the go-to tool for many credit modelers for good reason. GBMs can unlock meaningful lift in predictive accuracy, helping lenders better distinguish between high- and low-risk applicants, expand safe approvals, and reduce losses. But with great power comes great risk. At Ensemblex, we’ve spent years developing, testing, and monitoring GBM credit models. And while we remain strong advocates for their use in the right context, we also kno

Why Sponsor Banks Matter So Much Choosing a sponsor bank isn't just another box to check. It’s a consequential decision that influences your compliance obligations, user experience, and product velocity. The right sponsor can save you months of delay (and a lot of rework). But it’s not always obvious what you should be looking for—or what they’re looking for from you. Let’s break it down. What You Should Look for in a Sponsor Bank When evaluating the compatibility of a pote

At Ensemblex, we work with lenders across the fintech ecosystem — from startups to scaled portfolios — and we see many people making the same mistakes when measuring risk on revolving credit products. These mistakes lead to bad decisions, mispriced risk, and inaccurate expectations for portfolio performance. Here are some of the most common pitfalls and how to avoid them. 1. Measuring Risk “Vertically” Instead of Horizontally Many lenders look at risk in time slices — delinqu

Yes — if you bring unique insights, clear conviction, and extreme curiosity, you're a strong fit. In fact, Ensemblex has co-founded with several entrepreneurs that came outside of fintech. At Ensemblex, we back domain experts, technologists, and operators who do not rest until they fix a problem. Whether you're coming from sports, music, education, or engineering— if you’ve felt the friction, understand the user, and have a bold idea for how the world should evolve, you're ex

Your Loan Origination System Is One of the First—and Most Critical—Decisions The loan origination system is the first impression of a credit card or loan product. It’s where risk decisions are made, customer expectations are set, and compliance obligations begin. For early-stage fintechs, choosing a Loan Origination System (LOS) is about much more than picking the forms and workflows. It’s about building a flexible, modular process that balances speed, precision, and trust. H

FICO and Vantage scores are well-known, widely used, and easily accessible. Meanwhile, building a custom credit model can take significant resources. So why build your own? Let's dive into how FICO and Vantage work, how custom models differ, and why custom models can deliver meaningful performance gains. What Are FICO and Vantage? FICO and Vantage scores are generic, off-the-shelf credit scores built using credit bureau data from TransUnion, Experian, and Equifax. FICO has be