How a Personal Lender Expanded Its Buy Box Without Adding Risk

Pave helped a personal loan provider identify which marginal declines were actually approvable, enabling the lender to approve roughly 90% of that population without adding risk.

Get Demo
Instructions
If you intend to use this component with Finsweet's Table of Contents attributes follow these steps:
  1. Remove the current class from the content27_link item as Webflows native current state will automatically be applied.
  2. To add interactions which automatically expand and collapse sections in the table of contents select the content27_h-trigger element, add an element trigger and select Mouse click (tap)
  3. For the 1st click select the custom animation Content 27 table of contents [Expand] and for the 2nd click select the custom animation Content 27 table of contents [Collapse].
  4. In the Trigger Settings, deselect all checkboxes other than Desktop and above. This disables the interaction on tablet and below to prevent bugs when scrolling.
At a Glance
The Challenge

The lender was declining near-miss borrowers it could not confidently separate by risk. To expand responsibly, the team needed a sharper read on who was actually approvable.

The Outcome

Pave built a custom Personal Loan Score using the lender’s historical performance and consumer-permissioned cashflow data, helping approve roughly 90% of marginal declines without adding risk.

The Pave Impact
Performance compounds with each risk event on the Pave network

Over 1 billion monthly transaction and outcome events feed back into our models, resulting in sharper categorization, attributes, and scores that help separate risk within marginal personal loan applicants.

Customized for your book

We built the Personal Loan Score around the lender’s borrowers, historical performance, and the specific repayment risk it was underwriting, no black box, no one-size-fits-all.

We become an extension of your risk team

We monitor lift, spot drift early, tune thresholds, and ship new versions so the lender can keep finding approvable borrowers within its marginal-decline population as performance data accrues.

The Full Story

Challenge

For a personal loan provider, growth only works if credit performance holds. Expanding approvals without a sharper read on risk creates losses that outweigh the incremental volume.

The lender’s existing model helped sort applicants by risk, but left a gray area: marginal applicants who were close to approval, yet still treated as declines. Some of those borrowers looked risky through traditional credit attributes, even though their cashflow behavior suggested they could repay.

The lender needed a more targeted way to decide which marginal declines were actually approvable before widening access.

Solution

Pave partnered with the lender to build a custom Personal Loan Score around its own performance data and underwriting workflow.

  • Portfolio-specific model training: The score was trained on the lender’s historical loan performance, making it specific to the lender’s book rather than a generic market score.
  • Consumer-permissioned cashflow data: Pave used bank transaction and balance data to add a real-time view of borrower financial behavior, including signals like income stability, cash reserves, fee activity, balance trends, spending pressure, and repayment capacity.
  • Ongoing performance feedback loop: As the lender shares performance data back to Pave, both teams will monitor results, refine the model, and keep the score aligned with real portfolio outcomes over time.

Results

Pave’s analysis showed that cashflow data could separate risk inside the lender’s marginal-decline population, turning a gray area into a clearer approval opportunity.

  • ~100k loans analyzed: The custom score was validated against historical loan performance and cashflow data.
  • 90% of marginal declines approved: More near-miss applicants could move forward without adding risk.

Conclusion

The lender did not need another generic credit score. It needed a sharper way to decide which marginal applicants were actually approvable.

By building a custom Personal Loan Score on the lender’s own performance data and applicant cashflow, Pave helped the lender approve more near-miss borrowers while keeping risk aligned with real portfolio performance.

See what a score built for your book can do

Off-the-shelf scores you can deploy today, sharpened by every lender on the network.

Get DemoSee all case studies →
learn more

Explore Use Cases

Drive growth with Cashflow-driven Analytics

Use our Cashflow-driven Attributes and Scores to provide timely, borrower-specific insights tailored to your lending criteria. Make informed decisions that enhance approval rates and loan performance.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.