Employee Wellness, Performance, and Retention Analysis

This project aimed to explore the relationships between employee wellness usage, performance ratings, and retention within a corporate setting. By analyzing these relationships, the goal was to provide actionable insights that could help enhance employee well-being, productivity, and retention, particularly focusing on high-level employees such as Directors+.

1. Correlation Analysis: Understand the relationships between wellness usage, performance ratings, flight risk, and other variables.

2. Hypothesis Testing: Test specific hypotheses related to performance, flight risk, and gender differences in wellness usage.

3. Predictive Modeling: Build models to predict employee retention based on wellness usage and other factors.

4. Survival Analysis: Analyze the tenure of employees in relation to their wellness usage and performance ratings.

- Data Collection and Preparation: Collected and cleaned a comprehensive dataset comprising multiple Excel files with 42 columns of employee-related data.

- Exploratory Data Analysis (EDA): Utilized descriptive statistics and visualizations to understand data distributions and relationships.

- Statistical Analysis: Performed correlation analysis, hypothesis testing, regression analysis, and survival analysis to assess the relationships between wellness usage and other variables.

- Visualization: Created heatmaps and color-coded correlation tables to effectively communicate findings. Exported these visualizations to Excel for client use.

1. Performance and Wellness: High-performing employees were found to have a statistically significant difference in wellness days used compared to low performers.

2. Flight Risk: Directors+ with higher flight risk tend to use more wellness days, indicating a potential area for targeted interventions.

3. Gender Differences: Gender-based analysis revealed significant differences in wellness days used, suggesting the need for gender-specific wellness programs.

- Python (pandas, seaborn, matplotlib, SciPy, statsmodels, lifelines)

- Jupyter Notebook

- Microsoft Excel

- Data Integration: Managed multiple data sources with different structures, ensuring clean and merged datasets for analysis.

- Handling Missing Data: Implemented strategies to address missing values and categorical data issues to ensure robust statistical analysis.

The insights from this analysis can help HR departments to:

- Design more effective wellness programs.

- Implement targeted interventions for high-risk employees.

- Enhance overall employee retention and performance.

This project underscored the critical role of data-driven approaches in managing employee wellness and retention. By understanding the nuanced relationships between various HR metrics, organizations can foster a healthier, more productive workforce