Logistics Intelligence Series | Module 3 of 6

Driver turnover:
Who resigns in 90 days?

Replacing a truck driver costs €12,000–€18,000. And the market is empty. This model identifies from shift plans, telematics and overtime data which drivers you will lose in the next 3 months - before the resignation letter lands on your desk.

01 The most expensive problem in the industry

Driver shortage is not new - but the hidden patterns behind it are

Turnover in road freight stands at 25–35% per year. For a fleet of 150 trucks that means: you lose 40–50 drivers every year and must replace them. The cost per departure - recruiting, onboarding, vehicle idle time, colleagues' overtime - is €12,000–€18,000.

But: resignations rarely come from nowhere. There are patterns in the data that are visible weeks in advance - if you look. Not in a dispatcher's gut feeling, but in the numbers your system already captures.

40 drivers × €15,000 = €600,000/year

If you prevent just 8 resignations, that saves €120,000 - and stabilises your route planning.

HR Data
Shift plans
Telematic patterns
Churn model
Risk Score
Intervention

02 Data foundation - what HR and dispatch know together

The decisive link: personnel data + operational data + behavioural patterns

We combine three data sources that exist in every logistics company but are never analysed together: HR master data, shift-planning exports and telematics behaviour data. The simulation covers 210 drivers over 24 months.

▸ Output
Dataset: 5.040 Monatsdatensätze, 210 Fahrer
Fluktuation: 28.6% über 24 Monate (60 Fahrer)
FahrerAlterBetr.Zug.PendelSchichtÜberst.KrankWE-SchichtenHarsh Brake
F-012271.2 J50 minFernverkehr28.3h1314
F-045518.7 J25 minNahverkehr12.1h028
F-089342.3 J70 minFernverkehr22.6h3419
F-103446.1 J15 minWechselbrücke14.8h0110
F-167240.8 J35 minNahverkehr19.4h1311

03 Exploratory analysis - what leavers have in common

Patterns that no performance review makes visible

Leavers vs. stayers - behavioural difference (3 months before resignation)
↳ The Early Warning Signal

3 months before resignation drivers show a clear pattern: +85% more sick days, +67% more harsh-braking events and a 28% decline in willingness to work overtime. These are not coincidences - they are the data-based "internal departure" from the company.

Turnover by length of service
↳ The Critical Phase

Drivers with less than 1.5 years' tenure have a turnover rate of 42%. After 4 years it drops to 15%. The first 18 months are the danger zone - and exactly where targeted intervention has the highest ROI.

Turnover risk by shift type × commute time

04 Feature engineering - reading the behaviour

16 features from three data sources that together form a picture

▸ Output
Feature-Matrix: 16 Features × 5.040 Monatsdatensätze

The key: trend features. Not the absolute value matters ("3 sick days") but the change ("1 more sick day than the 3-month average"). A driver who suddenly takes more sick leave than usual sends a stronger signal than one who has always taken a lot.

05 Model - random forest + survival analysis

Two perspectives: who leaves? And when?

We train a Random Forest Classifier for the 90-day prediction ("does this driver resign in the next 3 months?") and complement it with a Kaplan-Meier survival analysis for the question "how likely is it that this driver type is still here after X months?"

0.847
Precision
0.812
Recall
0.829
F1-Score
0.934
AUC-ROC
↳ Interpretation for HR

Recall 81.2% means: the model identifies 4 out of 5 upcoming resignations in advance. Precision 84.7%: when it flags "risk", it is correct in 85% of cases. The few false positives are drivers who are dissatisfied but (still) staying - a conversation is worthwhile here too.

Feature importance - what the model reveals about your drivers

The change in sick days is the strongest single predictor - stronger than tenure or salary. A driver who suddenly takes more sick leave is in all likelihood already job-hunting. But: it is the combination of sick-day trend + declining overtime + increasing harsh-braking events that makes the model so accurate.

06 Risk dashboard - your 10 most at-risk drivers

What the monthly report for fleet manager and HR would look like

The model scores every driver monthly with a churn risk score of 0–100. Drivers above 70 are flagged as "high risk" - a one-to-one conversation should happen within 2 weeks.

147
Low risk (0–30)
38
Medium risk (30–70)
25
High risk (>70)
210
Drivers total
F-012 · Long-haul · 1.2 years
⚠ Churn Risk Score
87 / 100
Driver: Sick days +120% vs. prev. quarter · Overtime –35% · Harsh Braking +45% · Commute 50 min · Tenure only 1.2 years · Age 27 (high mobility)
F-089 · Long-haul · 2.3 years
⚠ Churn Risk Score
79 / 100
Driver: Commute 70 min (highest category) · 2 complaints in 3 months · Sick days +80% · Speeding violations doubled
F-167 · Local delivery · 0.8 years
Churn Risk Score
62 / 100
Driver: Tenure under 1 year (critical phase) · Weekend shifts above average · Age 24 · Overtime volatility high
F-045 · Local delivery · 8.7 years
Churn Risk Score
12 / 100
Stability: Long tenure · Stable patterns · Short commute · No complaints · Consistent driving behaviour
↳ Recommendation: F-012

Driver F-012 shows the classic pre-churn pattern: young (27), short tenure (1.2 years), long-haul, long commute. The data calls for an immediate conversation. Options: transfer to local routes (reduces time away from home), adjustment of weekend shifts, or a concrete development discussion. Estimated cost of resignation: €15,200. Cost of a conversation + route adjustment: €0.

07 Survival analysis - when does it become critical?

Kaplan-Meier curves show which groups you lose first

Kaplan-Meier survival curve - retention probability by shift type
↳ What the Curve Reveals

After 18 months only 62% of long-haul drivers are still with the company - compared to 78% for local drivers. The steepest drop occurs between months 6 and 14. That is the period in which it is decided whether a driver stays. Targeted retention measures in this window have the highest ROI.

08 Business impact - the retention calculation

What it costs to lose drivers - and what it yields to keep them

Cost breakdown: what losing a driver really costs
€255.000
Net savings / year
19 drivers
Resignations prevented
ItemValue
Resignations/year (without model)60 drivers
Detected by model (81.2%)49 drivers
Retained through intervention (40%)19 drivers
Cost per driver loss€15.200
Gross saving (19 × €15,200)€288.800
Intervention costs (19 × €1,800)– €34.200
Net saving per year€254.600
↳ The Real Value

The €254,600 covers only direct costs. Not included: the stability of your route planning (fewer re-routes, fewer customer failures), the better team morale (fewer overtime stand-ins) and the competitive advantage in the labour market ("They care"). In an industry where every second haulier is looking for drivers, that is priceless.

09 Data protection & implementation

A sensitive topic - done right

Driver turnover is a people issue, not a pure data problem. The model does not replace a conversation - it shows you who to speak with. Implementation requires a careful touch:

① Connect data sources

Merge HR master data + shift planning + telematics in anonymised form. Ensure GDPR-compliant processing. Involve the works council.

② Monthly risk report

Confidential report to fleet manager + head of HR. No scores shared with dispatchers. The model is a leadership tool, not a surveillance instrument.

③ Intervention toolkit

Pre-defined measures per risk level: conversation, route adjustment, shift change, training, incentive scheme. Make measurable what works.