Fee prediction projects how much of the term’s demand is likely to be collected by a given date, from your own history of payment timing, instalment structure and prior-year behaviour. It is a cash-flow planning aid for the bursar, and it is deliberately not shown against individual families.
A projection is not a judgement about anyone. It is not used to score families, gate admissions or prioritise chasing, and it does not appear on a student record.
A bursar planning a quarter needs to know roughly what will land and when. That is a forecasting problem with a clear answer. The moment the same model is pointed at individual families it becomes something else entirely, and we do not build that.
Payment timing distributions from prior terms, the current instalment calendar, the concession and RTE position, and the shape of collection so far this term. Out of that comes a projected total by date, expressed as a range rather than a single figure, with the assumptions visible so a bursar who disagrees can see what to disagree with.
It is trained on your school’s own history. There is no cross-school model, because a school in a different city with a different fee structure tells you nothing useful about yours and pooling that data would mean sharing it.
No per-family default score. No ranking of students by likelihood to pay. Nothing of this kind on a student record, visible to a teacher, or usable in an admission decision. A family in temporary difficulty must not become a label that follows their child through the school.
This is a product rule, not a configuration option, and it is the reason the forecast stops at class level. Where a school wants to prioritise follow-up, the ordering is by amount outstanding and days overdue — facts, not predictions.
Phrased the way they arrive, answered so each one stands on its own.
No, and it will not. Prediction is aggregate — school, class or fee head. Follow-up is ordered by amount and days overdue, which are facts.
No. Projections are computed from your own history. There is no cross-school model and no pooling.
It improves with history and is stated as a range. A school in its first term has little to project from, and the forecast says so rather than producing a confident number from nothing.
Checked by the Implementations desk on 6 September 2026. Corrections go in the page, dated, rather than quietly.
Pricing is on the page, in the open, with the counting rule written next to it. Nobody has to book a call to find out what it costs.
See pricingForty minutes with an implementation engineer — your classes, your fee heads, your grading scheme, entered as we go. No slides, no sample school.