Prediction of Employee Attrition

The goal of this work is to analyse how objective factors influence employee attrition, and to
be able to predict whether a particular employee will leave the company with better accuracy
and generalization than existing models.
After the training, the obtained model for the prediction of employees’ attrition is tested on a
real dataset provided by IBM analytics, which includes 35 features and about 1500 samples.
Results are expressed in terms of classical metrics and using the stacked ensemble model we
achieved an accuracy of 88.4%, which was more than any other existing model using any
individual algorithms.
Data visualization is done for a clearer understanding.
The conclusions are also presented in visual form as correlation matrix.