Forecasts & anomalies
Path: HR Analytics Overview / Role Center → Charts
This family looks forward and for the unexpected. Forecasts project an indicator's future from its own history; anomalies flag periods that break the established pattern. There are two kinds of anomaly detection — a built-in statistical method and a machine-learning method — so you can pick whichever suits a given indicator.
How to read a forecast
A forecast projects the coming periods of an existing indicator and is shown as a central estimate plus a confidence range (a lower and an upper bound). On a chart the estimate is a line and the bounds form a band around it.
Treat a forecast as guidance, not a commitment. The band shows the uncertainty; the wider it is, the less certain the projection. Forecasts of externally-driven measures (turnover, labour cost) are inherently less precise.
Forecasts are powered by the SMART ML Forecast service and require the source indicator to keep at least 24 periods of history (set its Lookback Periods to 24+). Each forecast names the statistical model it uses by default (ARIMA, ETS, STL for seasonality, or a combination) — this is configurable.
| Forecast | Projects | From | Default model |
|---|---|---|---|
| Headcount Forecast | Total headcount | WRK-HEADCOUNT | ARIMA |
| Turnover Rate Forecast | Rolling 12-month turnover | WRK-TURNOVER-12M | ARIMA |
| Payroll Fund Forecast | Payroll fund (ФОП) | PAY-FUND | ETS+ARIMA |
| Payroll by Dept Forecast | Payroll for the top 5 departments | PAY-FUND (per unit) | ETS+ARIMA |
| SSC Forecast | Employer SSC (ЄСВ) | PAY-SSC | ETS+ARIMA |
| Total Labor Cost Forecast | Fund + SSC combined | PAY-FUND + PAY-SSC | ETS+ARIMA |
| Overtime Forecast | Overtime hours | WT-OVERTIME | ETS |
| Sick Leave Forecast | Sick-leave days | ABS-DAYS-SERIES (SICK) | STL |
| Vacation Days Forecast | Vacation days | ABS-DAYS-SERIES (VACATION) | STL |
| Absence Rate Forecast | Company absence rate | ABS-RATE-DEPT | STL |
| Labor Cost Budget Corridor | 12-month labor cost as a P10/P50/P90 probability corridor + three cumulative totals | PAY-FUND + PAY-SSC | ETS+ARIMA, percentiles 0.1,0.5,0.9 |
| Replacement Demand Forecast | Expected terminations next quarter (hiring-plan signal) | WRK-HIRES-TERMS (TERM) | Auto + intermittent detection |
| Vacation Liability Forecast | Vacation reserve, reported at the 90th percentile for accrual planning | ABS-LIABILITY | ETS+ARIMA, percentiles 0.5,0.9 |
| Headcount by Dept Forecast | Headcount per organizational unit (global cross-series model — new/small departments are covered too) | WRK-HEADCOUNT (per unit) | Global (ARIMA fallback) |
The last four ship disabled: enable them after the SMART ML Forecast connection is verified.
Advanced forecast options
Four options extend any forecast where the setup card shows them. They require the current SMART ML Forecast service.
- Forecast Quantiles — a comma-separated list of 2–3 percentiles in (0,1), for example
0.1,0.9or0.1,0.5,0.9. The published bounds then become those percentiles instead of the confidence band ("the value stays under X with ~90% probability"), and headlines switch to probabilistic wording. With three values the central estimate is the median. - Detect Intermittent — lets the service switch a sparse series (many zero months, e.g. per-department terminations) to a dedicated intermittent-demand model. Requires a single or empty (= Auto) Forecast Model — it cannot be combined with an ensemble.
- Use Calendar Regressor — feeds the number of working days per month (from the official payroll calendar in Human Resources Setup) into the forecast as a known future factor, so a 19-working-day month is not mistaken for a downturn. Requires Forecast Model = ARIMA or AutoARIMA, and the payroll calendar must be generated for the whole history and the forecast horizon — a missing month produces a clear error naming the calendar and the month.
- Use Global Model — for grouped forecasts (payroll or headcount by department): one cross-series model call covers all departments instead of one call per top-5 department, and departments with only a few months of history still get a forecast by borrowing strength from the others.
How to read an anomaly
An anomaly is a period that deviates from what the history predicted. Each anomaly row shows the actual value, the expected value and — for ML anomalies — the deviation type (seasonal, level shift, change-point, or trend). Severity follows the size of the deviation:
- 2–3 standard deviations → unfavorable;
- above 3 standard deviations → critical;
- a change against a perfectly flat history is treated as new behavior (ambiguous), not automatically critical.