Abhishek and Anurag introduce employee churn prediction in R. Roughly 25% of U.S. workers quit annually, and replacing someone costs 50-60% of their salary. The course covers turnover fundamentals, feature engineering, logistic regression modeling, and ROI calculation for retention using dplyr and ggplot2.
Chapters
Hi, I'm Abhishek. And I'm Anurag. We welcome you to our course on employee turnover prediction. Using r Employee turnover is all about an employee ending their formal relationship with an organization. In other words, turnover means gradual loss or exit of employees from an organization over a period of time. Generally, in the industry, employee churn, employee turnover and employee attrition are used interchangeably. Lets understand the impact of employee turnover. Employees are arguably the most important asset of any organization and one of the most critical issues organizations are facing today is how to retain their employees. Nearly 1/4 of all US workers quit their jobs every year and in some industries the turnover rate is considerably higher. As per the research by Society of Human Resource Management, replacing an employee can cost between 50% to 60% of that employee's salary, with overall cost ranging anywhere from 90% to 200%. In this course, you will learn how to use employee data to understand which employees are most likely to leave and use that information to design interventions to retain them. Before we get started, let's understand the types of employee turnover. Turnover is classified as voluntary and involuntary depending on the reasons for employee exit. When an employee chooses to resign on their own, it is an act of voluntary turnover. Involuntary turnover is when an organization decides to let go of an employee due to contractual obligations, business restructuring, or even due to disciplinary actions. Common reasons as stated by employees are finding better opportunities elsewhere, health, relocation, education and personal reasons. However, the underlying reasons for leavings are usually not shared by employees. That is, the actual drivers of turnover might be different. In this course, we will help you discover hidden reasons that might affect employee turnover such as relationship with manager, recent salary hike, received extra hours worked, distance from home to office, satisfaction with career and numbers of years in the company, etc. The course consists of four chapters. In chapter one we will cover the basics of employee turnover, how to calculate the turnover rate, explore and visualize the relationship of turnover with gender level, etc. And you will also learn how to bring different data sources together. In chapter two you will create new variables on also known as feature engineering and work on the concept of information value to identify important variables driving turnover. Chapter three focuses on building turnover prediction model using logistic regression and in the last chapter you will evaluate the accuracy of your model and classify employees in risk buckets. You will also calculate the ROI of interventions designed based on your recommendations. The course heavily relies on dplyr and ggplot2 packages for data manipulation and visualization. Now it's time to test your understanding of employee turnover but.
