Detecting billing anomalies in a services business
Contract, work-order and invoice data were reconciled, and an anomaly model now flags unbilled work and pricing errors for review each week, with a governance process for the model itself.
- Location
- Germany
- Duration
- 6 months
- 1.9%of revenue identified as leakage
- 73%of flagged items confirmed by analysts
- Weeklyreview cycle owned by the finance team
The challenge
Revenue leakage was suspected but could not be sized. Contracts, delivered work and invoices lived in three systems with no reliable common key.
What we did
We built a reconciled dataset linking contracts, work orders and invoices, with explicit rules for matching and a record of unmatched items.
Statistical and model-based anomaly detection surfaced unbilled work, out-of-contract pricing and duplicate charges, each with the evidence a finance analyst needs to act.
A weekly review workflow, performance monitoring and a retraining procedure were established so that the finance team owns the process.
The outcome
Recovered and prevented leakage in the first six months exceeded the cost of the engagement several times over. The analyst team now runs the process without external support.
A representative engagement. The figures are indicative of typical outcomes for this kind of work and are not drawn from a named client.
Contact
Tell us about the problem you need to solve
You may have a defined project, an underperforming process or a technical question that needs investigation. We can help assess the challenge, identify the information required and define an appropriate next step.