The objective of this project is to predict whether an employee is likely to quit based on contributing factors using a fictional dataset created by IBM data scientists. An EDA is created on Tableau for an interactive experience. After necessary data cleaning and preparation, the dataset is trained on 2 algorithms models for comparison, Decision Tree and Logistic Regression. In addition, feature selection is applied using Random Forest under the category of Embedded methods. These embedded methods are advantageous because they are highly accurate, have better generalizations, and are interpretable. With these advantages, I thought I would get the best accuracy using feature selection with Random Forest. Since there are 34 features, I wanted to extract the top 25 most impactful features.
