If an employee that you have invested so much time and money leaves for other companies, then this would mean that you would have to spend even more time and money to hire somebody else. Making use of data science and predictive modeling capabilities, if we can predict employee turnover rate it will save the company from loss.This project is to find out the employees who are going to leave their company and employees who are going to stay in their company.
Features of the dataset included all the relative information about the employees working in the organisation. For example, their job profile, years completed in the company, their recent managers, total working hours etc.
https://drive.google.com/drive/folders/1fmCqKr6DNqy8g3tvlFjMpXPix6f-sLAi
Feature engineering was done on features of dataset. These Feature engineering techniques were applied to make the dataset such that Machine Learning algorithms can have a maximum accuracy in predicting the turnover rate. These included dealing with missing and duplicate data, selection of important features, removal of outliers etc.
After successfull Feature engineering, a training data set and a testing data set were made. Training data set was used to train the Machine Learning models, and testing data set was used to find out accuracy of our model.
To run the tests, model was evaluated using confusion matrix, accuracy, precision, recall, f1_score.