Aggregate yes, individual no
Absence at team level follows patterns: seasonal illness, day-of-week effects, school holidays, the period after a bank holiday. Those are forecastable and directly useful for planning cover.
Predicting which named person will be absent is a different matter entirely. It is legally sensitive - absence frequently relates to health, which is special category data - and it invites treating people differently based on a prediction about their health.
We would not build the individual version, and would advise against commissioning one. The aggregate forecast delivers nearly all the operational benefit without the risk.
What drives the aggregate
- Season, with clear winter illness patterns
- Day of week, where Mondays and Fridays typically differ
- Proximity to public holidays and school terms
- Local circumstances - weather events, transport disruption
- Department and role, since physical and desk-based work differ
- Historic rate for that team, which is fairly stable
These give a usable forecast of how many people will be missing, which is what a rota planner actually needs.
Turning it into cover
| Forecast | Planning response |
|---|---|
| Expected absence count | Baseline cover level |
| Upper range on a bad day | Escalation plan, bank or agency arrangements |
| By skill or qualification | Which cover must be qualified, not just present |
| Seasonal peaks | Advance recruitment, holiday policy |
The skill dimension is often the binding constraint. Having enough people is irrelevant if none holds the required certification, and an aggregate headcount forecast will miss that entirely.
Keep it away from individual management
Even aggregate analysis can drift towards individuals if teams are small, and a forecast broken down far enough effectively identifies people. Set a minimum group size for any breakdown and hold to it.
Be equally careful with what gets shared. An absence forecast is a planning tool for rotas; it should not become an input to performance conversations, and the way it is presented should make that clear.
The causes matter more than the forecast
Forecasting absence helps you cope with it. Where rates are unusually high in a particular team or shift pattern, that is worth investigating as a cause rather than planning around indefinitely.
Aggregate analysis is genuinely useful here - identifying that one shift pattern or site has a persistently higher rate points at something specific, and fixing it is worth more than any amount of cover planning.
Forecast how many will be absent. Do not try to forecast who.