← Workforce Attrition Analytics

Business Case · People Analytics

Turning a risk score into a business case HR could act on

A single accuracy number doesn't tell HR who needs what. So the 294 held-out employees were broken into four real-world outcomes — and each one was priced.

Four scenarios on the hold-out set

Every one of the 294 held-out employees falls into one of four groups. That is how we briefed HR: not a single accuracy number, but who needs what.

192
Quietly fine Stayed · not flagged

No intervention. Confirms the model is not over-flagging.

55
False alarm Stayed · flagged

A brief, low-key check-in. Cheap even when the flag is wrong.

18
Missed entirely Left · looked low-risk

The blind spot — about 4 in 10 leavers. High-value roles still need a manual safety net.

29
Caught in time Left · flagged

Where the value lives. Retention conversation within days.

The business case

SHRM puts replacement cost at 50–200% of annual salary. Average pay in this dataset is about $57K. Of the 29 leavers the model caught, retaining even one in three — roughly 10 people — avoids about $290K to $1.1M in replacement cost. False alarms are conversations. Missed resignations are replacement cycles. That is why we optimised for recall, not accuracy.

The 84 flagged employees are not treated the same:

Low risk

Quarterly check-in for the HRBP. No urgency; logged for trend tracking.

Elevated risk

Retention conversation within two weeks. The human still makes the call.

High risk, high value

Escalate to manager and HRBP together — the costliest miss to allow.

Full HR leadership deck (PDF) →