Skip to main content

Employee Retention Use Case

A guide to implementing Auto Insights for an employee retention use case, including data structure and sample questions.

Auto Insights can help HR teams automate retention analysis, investigate employee turnover and identify attrition risks.

This article covers:

·   Example insights from this use case.

·   Recommended data structure for this use case.

What sort of insights can Auto Insights help me uncover?

We've outlined some example questions that Auto Insights can help answer through a combination of its proactive insights, Search, and What caused this? analysis:

Automate Retention Analysis

·   Average leaving probability by team

·   Show me terminations by department last quarter

·   Average years of service at termination by department

·   Number of terminations by department and office location

Investigate Employee Turnover
  • Average years of service by department

  • Number of terminations by rank and department

  • Leaving probability by rank and team

  • Quarter-on-quarter terminations by rank and department

Identify Attrition Risks
  • Number of employees by years of service and position

  • Leaving probability by rank last six months

  • Percentage growth of leaving probability by team this quarter

How Do I Structure My Data?
  • Auto Insights requires structured, transactional data, with at least 1 measure (for example, Years of service) and 5 segments (for example, Employee rank). In addition, we recommend at least 7 months of data (at monthly or daily granularity) so you can take full advantage of Auto Insights' Unexpected Changes feature.

Example Data Structure

Here are some of the typical segments we find in HR data. A segment is a qualitative value, like names or categories:

  • Employee attributes: Employee name, Manager name, employee rank, employee team name, employee department name, hire date, termination date, employee ID, employee age, employee gender, employee location, employment type, etc.


A measure is a quantitative, numeric value. Some of the typical measures include monthly salary, years of service, leaving probability, and more.