This chapter begins with a general introduction to employee churn/turnover and reasons for turnover as shared by employees. You will learn how to calculate turnover rate and explore turnover rate across different dimensions. You will also identify talent segments for your analysis and bring together relevant data from multiple HR data sources to derive more useful insights.

What is turnover?

Objectives of employee turnover prediction

Importing headcount and turnover data

Exploring the data

What proportion of employees have left?

Which levels have high turnover rate?

Is turnover rate different across locations?

HR data architecture

Filtering the dataset

Combining HR datasets (I)

Combining HR datasets (II)

Master data overview

Introduction

In this chapter, you will create new variables from existing data to explain employee turnover. You will analyze compensation data and create compa-ratio to measure pay equity of all employees. To identify the most important variables influencing turnover, you will use the concept of Information Value (IV).

Feature engineering

Derive age difference

Derive job hop index

Derive employee tenure

Compensation

Exploring compensation

Pay Gap

Deriving Compa-ratio

Deriving Compa-level

Information value

Calculating Information Value

Which variables are important?

Feature Engineering

In this chapter, you will build a logistic regression model to predict turnover by taking into account multicollinearity among variables. 

Data splitting

Split the data

Corroborate the splits

Introduction to logistic regression

Build your first logistic regression model

Build a multiple logistic regression model

Interpreting significance levels

Multicollinearity

Detecting multicollinearity

Dealing with multicollinearity

Building your final model

Building final logistic regression model

Understanding the model predictions

Interpret the results

Predicting Turnover

In this chapter, you will calculate the accuracy of your model and categorize employees into specific risk buckets. You will then formulate an intervention strategy and calculate the ROI for this strategy.

Validating logistic regression results

Create a confusion matrix

Accuracy of your model

Designing retention strategy

Calculate turnover risk probability

Creating turnover risk buckets

What would you do?

Return on investment

Create salary hike range

Calculate turnover rate across salary hike range

Calculate ROI

Wrap-up

Model Validation, HR Interventions, and ROI

Employee data

Organizational growth largely depends on staff retention. Losing employees frequently impacts the morale of the organization and hiring new employees is more expensive than retaining existing ones. Good news is that organizations can increase employee retention using data-driven intervention strategies. This course focuses on data acquisition from multiple HR sources, exploring and deriving new features, building and validating a logistic regression model, and finally, show how to calculate ROI for a potential retention strategy.

HR Analytics: Exploring Employee Data in R

Discover how to predict employee turnover and design retention strategies using feature engineering, logistic regression, model validation and more in R.

HR Analytics: Predicting Employee Churn in R

Predict employee turnover and design retention strategies. 

Information value	Predictive power
`< 0.15`	Poor
`Between 0.15 and 0.4`	Moderate
`> 0.4`	Strong

Which variables are important?

HR Analytics: Predicting Employee Churn in R

动手互动练习