philippdrebes / MSCIDS_MPM02_Project

MPM02 Applied Machine Learning and Predictive Modelling 1 | Group Project

MSCIDS MPM02: Employee Turnover Prediction

This is a group project for the module Applied Machine Learning and Predictive Modelling, as part of the Applied Information and Data Science masters program at the Lucerne University of Applied Sciences and Arts.

Project Overview

The aim of this project is to analyze a dataset containing employee turnover data and develop predictive models using various machine learning algorithms. The following algorithms will be used in this project:

• Linear Model
• Generalized Linear Model with family set to Poisson
• Generalized Linear Model with family set to Binomial
• Generalized Additive Model
• Neural Network
• Support Vector Machine
• Optimization problem

Dataset

The dataset we will be using is the Employee Turnover. This dataset contains information about the employees of a company such as 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 been promoted, their department, salary level, and whether they left the company or not.

Project Structure

• data/turnover.csv -> data set
• employee-turnover-prediction.Rmd -> RMarkdown file containing the analysis
• Employee_Turnover_Prediction.pdf -> RMarkdown file compiled as PDF
• README.md -> this file

Project Deliverables

The following deliverables will be submitted for this project:

• RMarkdown in PDF format
• RMarkdown containing all code and analysis
• README file containing project overview and instructions for reproducing the analysis

How to Reproduce the Analysis

To reproduce the analysis, follow these steps:

1. Clone the project repository: git clone https://github.com/philippdrebes/MSCIDS_MPM02_Project
2. Launch R Studio
3. Open the employee-turnover-prediction.Rmd file and run the cells in order.

Note: You may need to adjust file paths in the notebook to match your local file system.

Contributors

• Albesa Istrefaj
• Antonia Durisch
• Philipp Drebes

Acknowledgments

We would like to thank our professors for providing guidance and support throughout the project.