The Recipe to a Strong Model Development (Part 1)

by Guest Contributor 1 min read July 30, 2009

By: Tracy Bremmer

Preheat the oven to 350 degrees. Grease the bottom of your pan. Mix all of your ingredients until combined. Pour mixture into pan and bake for 35 minutes. Cool before serving.

Model development, whether it is a custom or generic model, is much like baking. You need to conduct your preparatory stages (project design), collect all of your ingredients (data), mix appropriately (analysis), bake (development), prepare for consumption (implementation and documentation) and enjoy (monitor)!

This blog will cover the first three steps in creating your model!

Project design involves meetings with the business users and model developers to thoroughly investigate what kind of scoring system is needed for enhanced decision strategies. Is it a credit risk score, bankruptcy score, response score, etc.? Will the model be used for front-end acquisition, account management, collections or fraud?

Data collection and preparation evaluates what data sources are available and how best to incorporate these data elements within the model build process. Dependent variables (what you are trying to predict) and the type of independent variables (predictive attributes) to incorporate must be defined. Attribute standardization (leveling) and attribute auditing occur at this point. The final step before a model can be built is to define your sample selection.

Segmentation analysis provides the analytical basis to determine the optimal population splits for a suite of models to maximize the predictive power of the overall scoring system. Segmentation helps determine the degree to which multiple scores built on an individual population can provide lift over building just one single score.

Join us for our next blog where we will cover the next three stages of model development:  scorecard development; implementation/documentation; and scorecard monitoring.

Related Posts

AI Agent Identity Verification: How to Verify AI Agents in Digital Transactions

AI agents are changing the way consumers interact with businesses online. Learn how you can establish greater confidence in AI transactions.

August 26, 2026 by Laura Burrows
Ask the Expert: Turning Insight into Advantage with Michelle Goeppner and David Elmore

What if some of your best potential borrowers are the ones your traditional credit strategy can't fully see? A credit score can tell lenders a lot about a consumer, but it doesn't always capture the full picture of how someone is managing their financial life. For consumers with nontraditional income patterns or limited credit histories, that incomplete view can mean missed opportunities. In this Ask the Expert session, David Elmore of Experian talks with Michelle Goeppner, Chief Lending Officer at Vantage West Credit Union, about how alternative data can provide additional context around consumer risk, uncover opportunities traditional data alone might miss and help lenders expand their reach without disrupting strategies that already work. Who could lenders be missing? That question is especially important when a consumer’s financial life doesn’t fit neatly into a traditional credit profile. Take gig workers. Someone driving for Uber or delivering for DoorDash likely has a different income pattern than a salaried employee — irregular, seasonal, spread across platforms. That doesn't mean they aren't reliably managing bills, rent and other obligations. It just means a traditional file may not show it. Goeppner has a name for the risk of overlooking that context: FOMM — Fear of Missing Members. You've heard of FOMO — Fear of Missing Out. I think about it as FOMM — Fear of Missing Members. Who are we leaving behind if we're not using it?Michelle Goeppner, Chief Lending Officer For credit unions especially, that's not just a data question — it's a mission question. A partial view of a member's finances can mean missing a member the institution exists to serve. The credit score alone doesn't tell you where someone's headed Traditional credit data is still  foundational to lending decisions. But alternative data — income, cash flow, payment behavior — adds a layer that a credit score alone can't provide. Goeppner illustrates the distinction with two consumers who have exactly the same credit score: I don't know if you're a 640 score on your way to 720 — or are you a 640 headed southwards to 580? It doesn't show me how you're managing your day-to-day financial lifeMichelle Goeppner, Chief Lending Officer Two borrowers can share the same score and be moving in opposite directions. Alternative data helps lenders tell the difference — and put that score in context rather than treating it as the whole story. Start small and layer it in Adopting alternative data doesn't mean overhauling an existing strategy. As Goeppner puts it, it's additive, not a replacement: It's not a rip and replace. You don't have to let go of your existing playbook. It's additive — you layer it in.Michelle Goeppner, Chief Lending Officer Her advice for getting started: Define the problem first. Are you trying to increase approvals, reach more underserved borrowers, or improve decisioning for a specific product? Test before you scale. Revisit loans you've already booked and ask whether alternative data would have changed the outcome — or pilot it on a single product before rolling it out further. Build in governance from day one. Document what changed, where the new data was used, and what results followed. As Goeppner puts it: “Crawl, walk, run. Slow and grow.” More loans without changing the risk profile For Vantage West, the value of that approach has shown up in its lending results. It has been an absolute game changer for us at Vantage West. We have been able to make more loans to our target members, our target segments, without changes to our risk profile.Michelle Goeppner, Chief Lending Officer That distinction matters. The goal isn't approving more loans for its own sake — it's having enough information to recognize good borrowers that traditional data alone would have missed. The result is a fuller picture of the people behind the credit file, and more confidence in deciding who a lender can serve. Explore alternative data with us Alternative data can help lenders add context to traditional credit information for a more complete view of consumers. Experian works with institutions of all sizes to incorporate additional consumer signals into existing lending strategies — strengthening decisioning, managing risk and identifying new opportunities for growth. Learn more Contact us About our experts Michelle Goeppner Chief Lending Officer, Vantage West Credit Union Michelle Goeppner is a dynamic financial services executive with over two decades of experience driving strategic growth, product innovation, and operational excellence across leading credit unions and financial institutions. Currently serving as the Chief Lending Officer at Vantage West Credit Union, Michelle leads the strategic vision for multi-billion-dollar consumer loan and deposit portfolios, as a member of the Executive Coalition. Her expertise spans consumer lending, product management, integrated marketing, and talent development, with a proven track record of leveraging fintech partnerships, automation, and data-driven strategies to optimize portfolio performance and member engagement. Throughout her career, Michelle has held pivotal leadership roles in organizations such as Alliant Credit Union and Discover Financial Services. She is recognized for her collaborative approach, detail-oriented execution, and commitment to developing future female leaders. Michelle’s contributions include founding Alliant’s Women’s Resource Group, serving on advisory councils and boards, and earning multiple industry awards for excellence and innovation. She holds an Executive Certification in Product Management from UC Berkeley, a Master of Science in Integrated Marketing Communications from Roosevelt University, and a Bachelor of Science in Marketing from Northern Illinois University. David Elmore Vice President of Fintech Sales, Experian David Elmore leads a team of fintech sales professionals at Experian focused on helping fintech organizations drive responsible, scalable growth through data-driven analytics and decisioning. With more than 20 years in financial services — a decade of it focused on fintech — he brings deep expertise in applying traditional and alternative data across the customer lifecycle. David and his team partner with fintech leaders to navigate opportunities across acquisition, underwriting, portfolio management, and collections, balancing innovation, risk, and trust.

August 26, 2026 by Julie Lee
Scam Detection 101: How to Spot Scam Schemes Before Customers Fall Victim

Explore five common scam schemes, the signals to watch for and how fraud teams can enhance scam detection.

August 25, 2026 by Laura Burrows

Subscribe to our Newsletter

Enter your name and email for the latest updates.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Subscribe to our Newsletter

Don't miss out on the latest industry trends and insights!
Subscribe