The HR Salary Prediction project is designed to assist Human Resources departments in making data-driven decisions regarding employee compensation. By leveraging machine learning models, this project predicts employee salary categories, which can be invaluable in setting competitive and equitable salaries.
- Predict employee salary categories based on years of experience, education level, and job role.
- Utilizes both Logistic Regression and Random Forest models for prediction.
- Offers insights into the most influential factors in determining salaries.
- Promotes fair and transparent salary predictions with fairness and bias mitigation techniques.
To get started with the project, make sure you have the following:
- Python 3.x installed
- Required Python libraries (provide a requirements.txt file)
- Access to the HR salary dataset (link to dataset or instructions for obtaining it)
We have employed two models for salary prediction: Logistic Regression and Random Forest. Logistic Regression offers interpretability, while Random Forest provides high accuracy.
Both models were evaluated based on accuracy, precision, recall, and F1-score. Random Forest achieved an accuracy of 82%, while Logistic Regression achieved 75%. This indicates that Random Forest provides more accurate salary predictions.