See what cashflow adds to Prosper’s personal loan decisions before you change one.

Pave Cashflow Scores predict near-term risk, meaning the next few installments, from bank transaction data. Run them alongside the Prosper Score on your own historical applications and get a measured read in 2–3 weeks. Credit policy doesn’t change.

Scope a backtest
1B+
monthly transaction and outcome events on the Pave network
10,000+
cashflow attributes, from unified bank, credit and performance data
2–3 weeks
from data to a measured read on your own book
0
changes to your credit policy to get started

Four places cashflow could earn a spot in Prosper’s decision

Verification is a risk decision, not just a step.
Income verification confirms a number at one point in time. A connected account shows whether that income arrives on schedule, how much it moves month to month, and how much is already committed before the next payment is due. That is the evidence a verification strategy needs to decide who can be auto-verified without adding risk, and who still needs documents.
Not every borrower’s income fits a pay stub.
W2 pay plus side income, gig earnings, deposits split across accounts. These borrowers can carry real ability to repay that is hard to document. Cashflow reads the pattern across every connected account rather than a single document.
A six-year loan is seventy-two next payments.
Longer terms lower the monthly payment and stretch the period each loan has to perform. Scoring near-term risk at application, then re-scoring the borrower as cashflow moves, shows which loans are drifting while there is still time to act.
Every approval has to hold up for the investors who fund it.
Investors buy Prosper’s loans for a specific risk profile. Approval growth only counts if losses stay inside that risk appetite, so any new signal has to be proven on Prosper’s own outcomes first.

How this fits what Prosper already runs

Scope a backtest
Alongside the Prosper Score.

Pave adds inputs to the models and policy you already run and replaces nothing. Scores and attributes are visible inputs, not a black box.

On the bank data you already collect.

Pave works on transaction data from the account connections already in your application flow. Borrowers don’t get a new step.

Into your own decision platform.

Scores and attributes arrive over API into your decisioning, or land in Snowflake for your analysts.

Tested the way you test anything new.

First a champion-challenger run on historical applications, then a randomized live test on a slice of traffic, measured against benchmarks you set. Policy changes only after that.

THE TEST

How we’d prove it on Prosper’s book

We won’t ask you to take a published result on faith. Prosper picks historical personal loan applications that connected a bank account, with their outcomes. Your current decision stays the champion, Pave scores the same applications as the challenger, and both are compared against what happened on the next few installments, including inside tiers your current grade treats alike.

2–3 weeks
to a read on where approvals could be added inside your risk appetite, and where losses sit inside approved tiers
0
policy changes before a randomized live test on a slice of traffic

Pave for Prosper’s personal loan book

Personal Loan Score
Predicts near-term repayment, the next few installments, at application, then re-scores the borrower as cashflow moves. The risk event and window are set with your team.
Cashflow Attributes
10,000+ measures of income stability, affordability, obligations and payment behavior, ready to feed the models behind the Prosper Score.
Income Prediction
Predicts the next deposit and when it lands, for affordability checks and setting payment dates.
API or Snowflake
Scores and attributes over API into your decision platform, or delivered to the Snowflake warehouse your analysts already use.
Credit Card Score
The same near-term read for line and early-deterioration decisions on the Prosper Card.
Ongoing Monitoring
Scores refresh as cashflow moves, so a 72-month loan is re-read across its term. The same score family covers small dollar, cash advance, SMB charge card and SMB ACH risk.

The Pave Impact

Proven before you commit: we validate the lift on your own book in 2–3 weeks, before you change a line of policy.

Scope a backtest
Performance compounds with each risk event on the Pave network
Over 1 billion monthly transaction and outcome events feed back into our models, sharpening categorization, attributes and scores.
Customized for your book
We build a custom score around your borrowers and the specific risk event you're underwriting—no black box, no one-size-fits-all.
We become an extension of your risk team
We watch the lift, spot drift early, tune thresholds, and ship new versions—always finding ways to improve performance before you have to ask.
‍

Measure the lift on Prosper’s applicants before you decide anything.

Send historical applications and outcomes, and get a read against your current decisions in 2–3 weeks. No policy change, no rollout commitment.

Scope a backtest

Scoped in one call

Measured against your current decision

No policy change to start