Welcome to the Paragon resources hub
Here you’ll find a collection of useful materials on the techniques and considerations when it comes to developing, implementing, using and managing credit risk models, as well as the latest Paragon opinion and industry developments.
Why the Model Lifecycle Matters More Than the Model Itself
In the first two articles in this series, I challenged a couple of assumptions that often shape discussions about modelling in banking.
The first was that the most persistent problems rarely sit within the algorithms themselves. The second was that governance, when properly designed and applied, is not the obstacle it is sometimes perceived to be. Taken together, these ideas lead to a fairly obvious question. If the problem is not really the model and it is not governance in isolation, then where does the friction actually come from?
Why Most Banks Get AI Governance Wrong - And How to Fix It
In a recent article, I wrote about how the biggest challenges in credit risk modelling rarely sit in the algorithms themselves, but instead arise from the way models are developed, documented and understood within organisations.
What becomes clear when you follow that line of thinking a step further is that many of the governance challenges banks face today are not separate issues at all - they are a direct consequence of that same underlying friction.
Paragon Releases Modeller 6.310
Paragon is pleased to announce the release of Modeller 6.310, the latest update to our credit risk modelling platform. This version introduces a range of enhancements designed to improve usability and support more efficient model development within the 6.3 framework.
This release reflects our continued commitment to equipping credit risk teams with powerful, transparent and intuitive tools for building and managing predictive models.
Why the Biggest Challenges in Credit Risk Modelling Aren’t in the Algorithms
After more than 30 years working in credit risk modelling and leading Paragon Business Solutions through much of that journey, one thing has become increasingly clear to me. The biggest challenges in modelling are rarely caused by the algorithms.
Most banks today have access to strong, well‑established techniques. Logistic regression, machine learning methods and Python libraries are widely available, mature and constantly improving. Yet when models struggle to gain traction, approval or long‑term credibility, the root cause is usually somewhere else. It sits in the space between the model and the organisation that is expected to trust it.
Can AI Agents Build Credit Risk Models as Well as Humans?
AI can now automate many technical credit risk modelling tasks from variable screening to model generation, but it cannot yet replace the human judgment required for explainability, data context and nuance, and compliance. The most effective approach is collaboration, combining AI’s speed and consistency with human expertise in context, regulation and reasonableness.
The Art and Engineering of Credit Risk Models
In credit risk modelling, it’s tempting to think that data alone holds all the answers and that more data automatically means better models. Feed enough data into an algorithm and it will “discover” the right relationships - or so the story goes. But experienced modellers know that data only tells part of the truth. It reflects past lending decisions, past customer behaviours, and past economic conditions, none of which perfectly represent the future.
That’s why good models aren’t just built; they’re engineered.
The Hidden Challenge of Reject Inference in Credit Scoring
When developing credit risk models, one of the hardest challenges is how to deal with rejected applications. These are the customers who applied for credit but were declined, meaning we never get to observe their true repayment behaviour.
Paragon releases Modeller 6.2
We are very pleased to announce that our latest major release of Modeller, version 6.2, delivering new functionality and usability improvements designed to further enhance the model development process. This release continues our commitment to providing credit risk teams with powerful, transparent, and efficient tools for building and managing their predictive models.
Fairness and Bias in Credit Risk Models
How to ensure credit risk models are fair and non-discriminatory presents an ongoing challenge and opportunity to lenders. With heightened regulatory attention and social awareness, lenders recognise the importance of avoiding the use of models that may exhibit undesirable bias, placing certain demographic and groups with protected characteristics as a systematic disadvantage in terms of their access to credit. The challenge is multifaceted: bias can be subtle, deeply embedded in historical data, and difficult to detect.
Performance with Transparency – successful credit risk modelling
For some, there's an ongoing temptation to equate complexity with sophistication and performance. More layers, more algorithms, more data - the assumption is that these always lead to better models. But what if the pursuit of complexity is actually undermining the very purpose of our models?
Transparency is not a checkbox to be ticked. It's a fundamental requirement that goes to the heart of how organisations make decisions, manage risk, and maintain trust with all stakeholders - from regulators to customers.
Beyond the Algorithms – successful credit risk modelling
While the technological capabilities of today's modelling systems are impressive, the real challenge lies not in building sophisticated algorithms, but in creating sustainable systems that operate effectively with trust and transparency. The most advanced credit risk model is worthless if it cannot be properly governed, maintained, or trusted by the people who depend on it.
What is Model Risk Quantification and why is it needed?
Model risk quantification (MRQ) is the process of assessing and measuring the uncertainty, limitations, and potential errors within a model. It provides organizations with a structured approach to understanding how much risk a model introduces and enables them to implement appropriate controls to mitigate its impact.
Model risk arises when a model fails to perform as expected, leading to inaccurate outputs that can result in financial loss, poor decision-making, regulatory non-compliance, or reputational damage.
The EU AI Act: Implications for Lenders and Credit Scoring Models
The EU Act for AI, also known as the AI Act, is a comprehensive regulatory framework proposed by the European Union to ensure the safe and ethical use of artificial intelligence (AI). Credit scoring models are likely to be classified as high-risk due to their significant impact on individuals’ access to financial services and economic opportunities. This classification brings about several regulatory requirements within the Act. These high-risk AI systems must meet specific criteria and adhere to strict regulatory standards.
Paragon releases Modeller 6.0
We are very pleased to announce that our latest major release of Modeller, version 6.0, was recently made available to all new and existing users. A new Model Explainer and reporting suite is included in this latest release. This enables users to run suites of model-agnostic reports on multiple models and/or populations simultaneously, driving efficiencies in the production and interpretation of reports.
Paragon: the credit expert’s choice
“We get value from Modeller due to its efficiency, time saving and auditing features.”
CARLIEN KRUGER, SENIOR MODELLER, WESTPAC
Find out why credit risk analytics experts choose Paragon software.
Our software
Whether you’re building and deploying models, automating decisions or managing model risk and governance, Paragon’s software comes with our no compromise, valued engineering built in.