This project aimed to address employee attrition concerns within a large company, XYZ, by leveraging HR analytics to understand and predict factors influencing employee turnover. With an annual attrition rate of 15%, the company sought insights to minimize talent loss, associated project delays, and recruitment challenges. The project involved extensive data analysis and predictive modeling to identify key factors contributing to employee attrition.Three distinct prediction models, employing advanced machine learning techniques, were developed and compared.
The models aimed to provide actionable insights for the management to focus on areas that would contribute most significantly to reducing attrition rates.Key findings from the analysis highlighted critical variables impacting attrition, including job satisfaction, work-life balance, and career growth opportunities.By prioritizing these factors, the management could implement targeted interventions to enhance employee satisfaction and retention.
The predictive models exhibited robust performance, with comparative evaluations aiding in the selection of the most effective model for guiding strategic decisions.In conclusion, the project offered a comprehensive understanding of the dynamics influencing employee attrition, providing XYZ management with actionable insights to foster a more engaging and satisfying work environment.The implementation of these recommendations has the potential to mitigate attrition challenges, ensuring a stable and productive workforce for the company's sustained success.
- Background
- Project Goals
- Key Features
- Data Sources
- Installation
- Usage
- Data Preprocessing
- Modeling
- Evaluation
- Results
- Recommendations
- Contributing
- License
XYZ Company faces a yearly attrition rate of approximately 15%, leading to various challenges such as project delays, recruitment efforts, and the need for employee training. The management seeks to identify and address factors contributing to attrition through HR analytics.
- Build predictive models to forecast employee attrition.
- Identify key factors influencing attrition.
- Provide actionable recommendations to reduce attrition rates.
- Development of three distinct predictive models.
- Comparative analysis of model performance.
- Actionable insights for management based on key findings.
The project utilized internal company data, including employee profiles, job satisfaction surveys, performance metrics, and historical attrition records .
-
Clone the repository:
git clone https://github.com/raghavendranhp/Attrition-Alchemy.git
2.Install the required Python packages
3.Deploy the Streamlit app on Streamlit Cloud by using the Streamlit CLI.
4.Access the deployed application--open app
- Execute the Jupyter notebooks in the notebooks directory in sequential order.
- Follow the data preprocessing steps to clean and prepare the data.
- Run the modeling notebooks to build and evaluate predictive models.
- The data preprocessing steps include handling missing values, encoding categorical variables, and scaling features.
- Detailed instructions are provided in the notebooks/preprocessing.ipynb notebook.
- The predictive models were developed using advanced machine learning techniques:
- Logistic Regression, Random Forest, SVM,Decision Tress and Gradient Boosting.
-
- Model performance was assessed using metrics such as accuracy, precision, recall, F1 score, and ROC AUC score.
-
- The results are discussed in the Attrition_prediction.ipynb.ipynb notebook.
- The project identified key factors contributing to employee attrition, providing actionable insights for the management to address workplace challenges and improve employee satisfaction.
- Comparative model analysis aids in selecting the most effective predictive model.
Based on the findings, the following recommendations are made:
- Focus on improving job satisfaction and work-life balance.
- Enhance career growth opportunities for employees.
- Implement targeted interventions based on department-specific attrition trends.
Contributions are welcome! For major changes, please open an issue first to discuss potential updates.
This project is licensed under the MIT License.
Open Application:https://attrition-alchemy-raghavendran.streamlit.app/
Raghavendran S,
Aspiring Data Scientist
LinkedIN Profile
raghavendranhp@gmail.com
Thank You !
Happy Enjoying !