The Next Big Thing In Credit Scores
Predictability, continuity and reliability are crucial prerequisites for successful credit scoring. Sound risk assessment decisions rely on credit score models that move with the times, evolving to reflect changes in consumer credit behaviour and improvements in risk prediction technology.
![](https://www.equifax.com.au/knowledge-hub/sites/default/files/Next%20Big%20Thing%20image2_1200x628px.png)
Equifax has recently launched Equifax One Score, developed to capture recent shifts in Australia’s data reporting and consumer credit behaviours. In the time since it was last updated, comprehensive credit reporting (CCR) has reached critical mass and a global pandemic has introduced unprecedented challenges to mortgage servicing and default management.
At the same time, data continues to grow in value as a strategic asset. Information and analytics are critical enablers in the race for financial service organisations to seize market opportunities and deliver customer-centric services. In this context, credit scores must develop apace, helping lenders ‘make sense’ of data by providing a complete and consistent picture of their customers’ credit risk.
More predictive power than ever before
Equifax One Score offers a substantial step up in functionality. Employing state of the art developments in explainable AI (xAI) and machine learning (ML) has brought about considerable improvements in the score’s predictive power and coverage. Modelling analysis indicates a 4.6% Gini uplift in predictive performance using the more powerful Equifax One Score compared to the current generation score. For credit card lenders, this improvement climbs to 8.4%; for personal loans even higher at 9.5%, and for residential mortgage portfolios a gain of 9.3% and for auto portfolios a gain of 6.5%.
As an example of the strength of these gains, we estimate1 credit card lenders could reduce their default rates by 16.35% using the new score based on an acceptance rate of 70%. Alternatively, the credit card loan approval pool (i.e. % of loan applications above the bureau score cut-off) could rise by 7.14% while maintaining the same default rate, or in other words, increasing the approval rate to 75% from 70% for the same level of risk . Our analysis shows that this improved predictability affords lenders the possibility of reducing their default rates or increasing their approval rates without increasing their risk.
As we look ahead to a changing landscape, Equifax One Score will give lenders the constancy and confidence to extend credit responsibly and innovate for competitive advantage. In turn, expanding the opportunities for consumers to live their financial best.
A solution to COVID-19 loan deferral uncertainty
The ongoing impact of coronavirus-induced loan deferrals and the expected rise in delinquencies reinforces the importance of a stable and highly predictive credit score to inform the loan origination and underwriting process.
Rather than relying on actual knowledge of whether an applicant is in arrears or not, a wide breadth of insightful data will give lenders the predictive power needed for business growth in today’s new normal. Over half a century as a credit reporting agency has allowed Equifax to build a rich tapestry of data assets into its scoring model, providing lenders with a more comprehensive and reliable understanding of credit risk.
Equifax is the market leader in consumer credit information, holding the largest collection of consumer credit related data, including CCR data, more than any other Australian credit bureau. In Equifax One Score, the latest CCR data augments our extensive repositories of negative event and enquiry data. These new positive data elements further refine the accuracy of the score, helping lenders navigate through COVID-19 uncertainties to quickly and easily identify which customers have the capacity to repay debt. The new scores have been developed to cope with limitations in recent CCR due to recent payment deferrals, and relies on both recent and longer term repayment history trends and up to five years of credit enquiry and defaults trends to ensure the score remains robust in these uncertain times.
Equifax also has the most contributors of Buy Now Pay Later (BNPL) data of any other Australian credit bureau. With consumers moving away from traditional credit products towards BNPL services, the predictive power of Equifax One Score will help lenders make meaningful gains in this rapidly growing market segment.
The opportunity to increase consumer financial literacy
A consistent and widely used credit score holds ongoing benefits for consumers to better understand their own role in determining their borrowing eligibility. With the rollout of open banking comes the opportunity for consumers to improve their financial wellbeing and embrace the importance of on-time, regular repayments of their credit commitments.
With more dependence on positive data and less on current enquiry data in this new generation score, there will no longer be such a disjoint between consumers and lenders requirements and expectations. For lenders taking a risk-based approach to pricing, for example, Equifax One Score offers greater consistency and reliability. Lenders carrying out pre-approvals before conducting a bureau check can be confident that when the applicant applies for a loan, they will get the same score.
As consumers begin to understand and accept that Equifax One Score is a dependable assessment of their creditworthiness, they will increasingly learn to leverage the value of data to negotiate on credit rates and terms. Within this transparent and effective ecosystem, lenders can personalise their engagement with customers, innovating on behalf of the consumer and driving decisions for profitable portfolio growth.
Reducing concerns about bias
In an environment of tighter regulation and growing concern about data-led bias, it is more important than ever for lenders to make compliant, informed and fair decisions when assessing credit risk.
Consumers, lenders and regulators want to understand how credit scores are determined, and importantly, whether the decision process is free from bias. This ability to explain the components of a decision hasn’t always been easy, but the development of NeuroDecisionTM Technology has now made it possible to leverage more powerful machine learning techniques than traditional Logistic/Linear Regression techniques and continue to be transparent and explainable.
NeuroDecisionTM Technology is a key feature of Equifax One Score. A ground-breaking explainable AI solution, it balances speed and accuracy with transparency and explainability. By applying this technology to our new generation credit score, we have been able to achieve both speed and power, while providing the distinct advantage of greater explainability. This unique ability to explain the elements of an individual score will foster trust in the validity of credit scoring, giving consumers the ability to understand how their credit behaviours influence the score outcome.
As part of our ongoing mission to ensure fair outcomes in credit scoring, there has been much work done to ensure the algorithms and processes behind Equifax One Score guard against bias. Rigorous testing has shown that neither age groups nor genders are unfairly represented in this new generation of credit score, giving lenders confidence that Equifax One Score is compliant with anti-discrimination legislation.
Speak to your Account Manager or email a One Score Sales Specialist to find out more.
1 This analysis does not consider lender policies or other underwriting criteria and uses the bureau scores as the sole criteria in loan approval for this comparison. The default rates are defined as any account that reaches 90 days past due or worse within 12 months after the date of the loan application being scored.
Related Posts
The ongoing housing crisis remains a hot topic and one of the major concerns for many Australians. Figures from Equifax1 confirm a troubling trend: home ownership in Australia becomes a progressively distant aim for younger people.
![Data cleansing, fixing spelling errors in customer names, removing deceased individuals from datasets, identifying duplicate records or reconciling inconsistencies are key for high quality data.](https://www.equifax.com.au/knowledge-hub/sites/default/files/styles/intro_image/public/field/image/Deathcheck%20BLOG%20article%20image_0.jpg?itok=jRvaE6Rp)
Businesses collect and process vast amounts of data, and often overlook the importance of ensuring the data is accurate, reliable, relevant, complete, consistent and timely. For a data-critical sector like insurance, the process of cleaning data to fix inaccuracies, incomplete, duplicate or wrongly formatted records holds valuable benefits.