Why the Conventional Credit Score Isn't Enough for Direct Mail Success

Traditional credit scoring models have long been the standard for assessing risk in lending. However, these conventional methods often present a trade-off, especially in pre-screen campaigns: tightening credit standards to reduce risk typically lowers response rates, while aiming for higher response rates can lead to an increase in defaults. This conventional inverse relationship can make it challenging for lenders to grow their customer base and improve profitability simultaneously. But what if there was a better way to identify and target promising borrowers who are often overlooked by traditional scoring?

The Limitations of Conventional Credit Scores

Conventional credit scores provide a single, linear view of creditworthiness. This can cause lenders to miss a significant portion of the market, specifically a group known as Invisible Primes™. These borrowers are inaccurately represented by low Bureau Score scores, despite posing a low credit risk. Relying solely on a conventional score can lead to:

• High-Bureau Score, Low-Conversion: Lenders might target individuals with high credit scores who are a good credit risk but have a low likelihood of responding to an offer.
• Low-Bureau Score, High-Risk: Conversely, focusing on individuals with low scores to boost response rates can result in a high rate of default.
• Mailbox Saturation: Too many lenders mailing to the same segment, leading to a competitive mailbox and low conversion across the board.

This is where the Trust Science approach, powered by alternative data and machine learning, offers a more advanced option that yields higher conversion and lower risk. Customer Acquisition services from Trust Science give you a data-driven differentiating edge, beating competitor offers and unlocking new growth opportunities.

The Power of the Customer Acquisition Dual-Score Matrix

Trust Science's Customer Acquisition services uses a dual-score matrix– a combination of conventional Bureau Score scores and its proprietary Six°Score™. By incorporating alternative data and improved propensity modeling, risk models can provide an orthogonal view of credit risk. This approach allows lenders to segment potential borrowers into four distinct categories:

Achieving Growth and Mitigating Risk

By implementing a dual-score model, lenders can achieve a vast improvement in campaign profitability. The ability to accurately identify Invisible Primes™ allows lenders to:

• Improve Response Rates: Target individuals who are likely to respond and repay, increasing the effectiveness of direct mail campaigns.
• Enhance Risk Performance: Safely approve more borrowers who were previously considered too risky by conventional models.
• Reduce Cost Per Funded Loan (CPFL): By focusing on a more profitable segment of the population, the cost of acquiring each new customer is reduced.

This advanced approach allows lenders to overcome the traditional dilemma of balancing risk and response rates. By strengthening customer acquisition channels and identifying significant bottom-line ROI opportunities, it has shown impressive results. A case study revealed a 27.9% higher portfolio yield and a 15.2% higher Return on Assets (ROA). Furthermore, it led to an 11% increase in approvals and a 13% reduction in defaults and achieved a threefold increase in conversion rates that boosted average earnings per customer by over 40%.

In Summary

The dual-score matrix, powered by alternative data and machine learning, is a game-changer for direct mail marketing in the lending industry. It moves beyond the limitations of conventional credit scores to reveal a hidden segment of profitable borrowers. By identifying and targeting these Invisible Primes™, lenders can not only improve response rates and reduce risk but also drive substantial improvements in campaign profitability and overall business growth.