2018 Excellence Awards Entry: Predicting Employee Attrition Using Human Resource Data
Overview of Use Case:
The model predicts the attrition of an employee based on various job-related factors.
Objective: The objective is to analyze the data and predict which valuable employees will leave next.
Fields in the Dataset include: Satisfaction Level; Last evaluation; Number of projects; Average monthly hours; Time spent at the company; Whether they have had a work accident; Whether they have had a promotion in the last 5 years; Departments (column sales); Salary; Whether the employee has left.
Describe the business challenge or problem you needed to solve
Predicting whether the employee will be leaving the firm or not.
Describe your working solution:
- R predictive tools.
- What data sources/formats are you using?: comma separated file
- Deploying an app on Alteryx Gallery?: No
- Using InDB tools?: No
- Are you exporting to a visualization tool?: No
Solution Steps:
- Separating independent (employee attributes) and dependent (left) variables
- Analysing principal components to get independent variables that have a correlation with the dependent variable
- Using Logistic Regression model to predict whether the dependent variable
- Getting the accuracy score of the predicted output vs actual output
- Result: 'Prob_Leave ' / 'X_1' probability of employee leaving & 'Prob_Stay' / 'X_0' probability of employee staying
-
Describe the benefits you have achieved:
Predicting whether the employee will be leaving the firm or not.
