Top model features
Drivers of attrition risk in your data
- Time since last salary review92
- Manager tenure / turnover81
- Engagement survey trend76
- Compensation vs market band68
- Skills growth (last 12 months)54
- Commute distance change38
Predictive Attrition
Machine-learning model identifying retention risks 90 days before they materialise.
High & critical risk
14
17% of workforce
Trailing 12m attrition
14.2%
↓ 2.4%Industry: 18.6%
Saves YTD
9
risk → retained
Model accuracy
82.4%
At-risk employees
Sorted by predicted 90-day attrition probability
| Employee | Score | Band | Top factors | Engagement | |
|---|---|---|---|---|---|
DW Daniel Wong Operations · 4.2 yrs | 84% probability | CRITICAL | Pay below marketNo promotion 3 yrs | 5.8 / 10 | |
YK Yusra Khan Finance · 1.8 yrs | 71% probability | HIGH | Manager turnoverSkill mismatch | 6.2 / 10 | |
RK Rohan Kumar Sales · 2.4 yrs | 68% probability | HIGH | Disciplinary caseBelow quota Q1 | 5.4 / 10 | |
MJ Maya Joseph Customer · 0.9 yrs | 62% probability | MEDIUM | Pay below marketShort tenure pattern | 7.1 / 10 | |
MA Mohammed Al Hashimi Operations · 1.2 yrs | 55% probability | MEDIUM | Disciplinary casesFrequent absences | 6.8 / 10 |
Department hot-spots
- Operations18.4%
- Sales16.2%
- Customer14.8%
- IT9.1%
- Finance6.4%