LUMINNOVATE

Monitoring and early warning.

Which customers are heading for trouble before they miss a repayment? Luminnovate watches each customer against its own normal and its peers, and says where a change happened before anyone explains why.

Arrears arrive after the warning signs have been in the account for months. A system that alerts on every dip buries the team; one that waits for a missed repayment is too late.

MonitoringOne borrower against its own normal and its peersAlert
below its own normalpeer band

Overdraft fees in the last 90 days: 3. Repayments: on time so far.

Illustrative example.

What Luminnovate does

  • Judges each customer against its own normalAnd against peers that operate the same way, so seasonal patterns stay quiet.
  • Forecasts delinquencyDelinquency forecasting across the book, with the drivers behind each customer's change and a range, monitored once live.
  • Holds false alerts to a budgetSet in advance, so the team can act on what it sees.
  • Shows where a change happenedBefore anyone explains why, so a regional fix is not mistaken for a book wide shift.

Two cases

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

81%Public bank data

Overdraft fees before missed repayments

of loans showing overdraft or penalty fees defaulted, against 7.3% of the rest

What was observed
Of 84 loans that missed a repayment, 33% had been overdrawn or charged penalty interest beforehand.
What a generic approach says
Wait for the first missed repayment.
What the engine read
Loans showing the fees defaulted 81% of the time, against 7.3% for the rest, and the flag caught all 3 defaults that never missed a repayment first.
What it meant for the decision
Fees in the account are an early sign worth watching. The numbers are small: this shows the mechanism, not a production signal.
3.65% to 0.04%Anonymised invoice data

The collections fix that looked like a model

invoices paid 30 or more days late

What was observed
Invoices paid 30 or more days late collapsed from 3.65% to 0.04%.
What a generic approach says
A book wide change in payment behaviour.
What the engine read
65% of the fall sat in one region, where 39% of invoices had run late and then none did.
What it meant for the decision
This corrected our own earlier reading of a book wide switch. Monitoring should show where a change happened before anyone explains why.

Start with a backtest on your own history: would it have seen your last bad quarter coming?

Book a conversation