Employee Turnover Prediction

Logistic Regression, Random Forest, and Gradient Boosting

Classification Model

Introduction

The HR department at Salifort Motors wants to take some initiatives to improve employee satisfaction levels at the company. They have the following question: what’s likely to make the employee leave the company?

Our objective in this project is to analyze the data collected by the HR department and to build a model that predicts whether or not an employee will leave the company.

If our model can predict employees likely to quit, it might be possible to identify factors that contribute to their leaving. Because it is time-consuming and expensive to find, interview, and hire new employees, increasing employee retention will be beneficial to the company.

All the files related to this project are available at Github.com/nitin6753/Employee_Turnover_Prediction

Summary

Objective:

Develop a machine learning model to predict employee turnover.
Identify factors that make the employee leave the company.

Tasks Performed:

Conducted extensive EDA, cleaned and structured the dataset for analysis.
Tuned hyperparameters of all models through grid search and cross-validation.
Developed an optimal Logistic Regression, Random Forest, and Gradient Boost model to predict whether employee will leave or stay.
Evaluated the model performance using validation sets, and then selected Gradient Boosting model as the champion by observing the evaluation metrics on test set.

Key Result Area:

Evaluated the model performance on validation sets, and then selected Gradient Boosting model as the champion, achieving a Recall score of 90.19% and other metrics including an accuracy of 96.82%, f1 of 90.55%, and precision of 90.91%.
Identified key features influencing employee retention:
1. Number of projects they have worked during their tenure, and
2. Tenure of employees,
3. Last evaluation of employees.

To retain employees,

Cap the number of projects that employees can work on.
Consider promoting employees who have been with the company for at least four years or conduct further investigation about why four-year tenured employees are so dissatisfied.
Either reward employees for working longer hours, or don't require them to do so.
If employees aren't familiar with the company's overtime pay policies, inform them about this. If the expectations around workload and time off aren't explicit, make them clear.
High evaluation scores should not be reserved for employees who work 200+ hours per month. Consider a proportionate scale for rewarding employees who contribute more/put in more effort.

Skills Demonstrated: EDA, Logistic Regression, Tree Based ML Algorithms, Hyperparameter Tuning, Cross-validation.

Feature Importance

Model Comparison: Validation and Test data

Confusion Matrix

Home

Page updated

Google Sites

Report abuse

Employee Turnover Prediction

Introduction

Summary

Objective:

Develop a machine learning model to predict employee turnover.

Identify factors that make the employee leave the company.

Tasks Performed:

Conducted extensive EDA, cleaned and structured the dataset for analysis.

Tuned hyperparameters of all models through grid search and cross-validation.

Developed an optimal Logistic Regression, Random Forest, and Gradient Boost model to predict whether employee will leave or stay.

Evaluated the model performance using validation sets, and then selected Gradient Boosting model as the champion by observing the evaluation metrics on test set.

Evaluated the model performance on validation sets, and then selected Gradient Boosting model as the champion, achieving a Recall score of 90.19% and other metrics including an accuracy of 96.82%, f1 of 90.55%, and precision of 90.91%.

Identified key features influencing employee retention:

Recommended:

To retain employees,

Cap the number of projects that employees can work on.

Consider promoting employees who have been with the company for at least four years or conduct further investigation about why four-year tenured employees are so dissatisfied.

Either reward employees for working longer hours, or don't require them to do so.

If employees aren't familiar with the company's overtime pay policies, inform them about this. If the expectations around workload and time off aren't explicit, make them clear.

High evaluation scores should not be reserved for employees who work 200+ hours per month. Consider a proportionate scale for rewarding employees who contribute more/put in more effort.

Skills Demonstrated: EDA, Logistic Regression, Tree Based ML Algorithms, Hyperparameter Tuning, Cross-validation.