Renewals and existing customers.

At origination a lender sees a few months of statements. At renewal it has years of the customer's own behaviour. Luminnovate reconciles that history, forecasts delinquency for the renewal decision from changes against the customer's own normal, and finds the right limit and offer before the customer asks.

The same evidence that flags stress also finds the customer ready to grow.

Renewals are often decided on the same thin view as a new application, while the lender already holds the strongest evidence there is: how this customer has behaved, and whether they serviced the facility they were given.

At originationThree months of statements

Trendunknown

At renewalTwo years, four statement sets reconciled into one history

12 month delinquency forecast6.8%, range 4.9 to 9.2%

Trend, seasonally adjusteddown

Bufferthinning

Customer concentrationrising

ATO and supplier paymentsslipping

Illustrative example. Harbour Joinery is a synthetic business.

Four applications, one history

Each time Harbour Joinery applied, it sent six months of statements. The sets overlap in places and leave gaps in others. Reconciled, they become one history, and every signal can be measured across all of it rather than the latest six months alone.

Statement sets on fileHarbour Joinery Pty Ltd4 sets, Sep 2024 to Aug 2026

Signal	Latest six months alone	Across the whole history
Receipts	Lower than in March	Below the same months last year, after seasonality
Cash buffer	11 days of outgoings	24 days a year ago: thinning
Largest customer's share	36%	22% when the first loan was approved: rising
ATO payments	Paid, 9 to 14 days late	On time until February: slipping
The facility it was given	Not visible	Every repayment on the first loan met

Illustrative example with invented data. Harbour Joinery is a synthetic business.

Several windows, one decision dateEach signal is measured over the recent quarter, the quarter before it and the customer's own year, using only what was known on the decision date. Windows sized to each customer's own cadence are designed to follow.
Gaps are reported, not bridgedA comparison with the customer's own normal, or with the last approval, is never made across a reported gap.
Signals earn their placeEvery signal is tested for lift, stability and leakage against the decision date before it is used. See how signals are created and tested.
The benefit, measured on your bookForecasts from the full history are compared with forecasts from the latest statements alone, on renewals you have already decided, before anything changes.
Across the whole bookThe same history and forecast for every facility due for renewal, ranked by risk and value: see the renewal book.

What Luminnovate does

Reconciles one historyOverlapping statement sets are joined, overlaps counted once and gaps reported, never filled. A missing statement is not a quiet month.
Forecasts delinquency for the renewalFrom changes against the customer's own baseline and since the last approval: trend adjusted for seasonality, a thinning buffer, customers becoming more concentrated, payments to suppliers and the ATO slipping. The engine chooses the method the data supports, explains the drivers, and is judged by the decision it improves.
Reviews limits and offersLimits sized to the evidence, and offers to existing customers before they ask, each with its reasons. Across the whole book, see the renewal book.

Two cases

Results from Luminnovate's work, labelled by source. Unlike the illustration above, these figures are not invented.

$231,704Synthetic business

The builder whose loan masked a fall

fall in revenue hidden inside a small dip in money in

What was observed: Total money in fell only $62,176.
What a generic approach says: A small dip in an otherwise steady business.
What the engine read: A $169,528 loan settlement masked a $231,704 fall in revenue. Three customers who paid $200,493 from January to June 2025 stopped paying, and the main customer fell from $270,908 to $156,108. A new daily facility of $1,520.76 was found from its pattern alone: 59 payments since May 2026.
What it meant for the decision: Eight grounded questions for the credit officer, each tied to the evidence behind it.

Read the full case

25 / 100Synthetic business

The contractor and the cafe

what a generic threshold scores 34 negative balance days in 180

What was observed: 34 days with a negative balance in the last 180.
What a generic approach says: A generic threshold scores it 25 out of 100: high risk.
What the engine read: For a contractor waiting on progress claims, that is normal. For a cafe settling card payments daily, it would be alarming. A collapse in trading across January matched an industry wide construction shutdown, and was expected.
What it meant for the decision: Each customer is judged against businesses that operate the same way, so an ordinary pattern is not read as risk.

Read the full case

Where it is used: Banks and lenders
One case: The builder whose loan masked a fall (Synthetic business)
Trust: How explanations are made and tested

Start with renewals you have already decided. We reconcile their histories inside your environment and show what the forecast would have said, from the full history and from the latest statements alone.

Book a conversation