Data-Driven-Insights-into-Job-Satisfaction-and-Compensation-Trends

This project analyzes 2020 employee data to identify factors influencing job satisfaction, performance, and salary differences, offering insights for improving engagement and workplace strategies.

About the Data

This analysis focuses on employee data from 2020, covering salary and job satisfaction across various industries, job roles, and geographical locations. The dataset was carefully chosen to ensure a balanced representation of categorical (e.g., job title, employment type) and numerical variables (e.g., salary, age), which allows for a detailed multidimensional analysis.

The goal of this analysis is to identify factors that influence job satisfaction, work-life balance, and overall employee performance. By employing statistical tests, factor analysis, and clustering techniques, we provide insights that can inform organizational strategies for improving employee satisfaction and performance.

This Dataset was downloaded from Kaggle: https://www.kaggle.com/datasets/ruchi798/data-science-job-salaries

Data Dictionary

🎯 Objective

The main objectives of this project are:

1. To identify which variables significantly impact employee satisfaction, salary, and performance.
2. To understand how these variables can be used to improve organizational strategies in terms of salary management, employee engagement, and work-life balance.

Performed Tasks

The following steps were taken as part of the analysis:

1. Data Cleaning & Preparation

• Cleaned the dataset by handling missing values, outliers, and formatting issues. I selected a limited number of rows based on assignment requirements and added variables to enable factor and cluster analysis.
• Converted some variables to an appropriate format for analysis like Performance Rating, Work Life Balance.

2. Exploratory Data Analysis (EDA)

• Non-Graphical Analysis: Initial checks on data distribution and summary statistics of numerical data.

• Visual Analysis:

1. Univariate Analysis: Plots for individual variables like experience level, work arrangements, and salary.
2. Bivariate Analysis: Examined relationships between key variables, such as salary by experience level and job satisfaction by work arrangement.

3. Hypothesis Testing

Formulated and tested hypotheses to explore relationships between variables such as:

• Differences in salary across experience levels.
• Impact of remote work on work-life balance.
• Engagement levels across different job titles.

4. Factor Analysis

• Used factor analysis to reduce the number of variables and uncover underlying relationships between employee ratings (e.g., job satisfaction, performance, remote work effectiveness).

• Extracted three main factors:

1. Remote Work Dynamics
2. Work-Personal Life Balance
3. Growth and Performance Perception

5. Cluster Analysis

• Applied K-means clustering to segment employees into distinct groups based on their engagement, satisfaction, and performance.
• Identified three primary employee clusters with unique characteristics, helping to tailor strategies for improving satisfaction and performance.

📊 Insights & Hypothesis Testing

We performed the following tests to validate our findings:

T-Tests:

• Hypothesis 1: Compared average salaries between entry-level and senior employees, confirming a significant difference.
• Hypothesis 2: Tested the effect of work arrangements (remote vs. non-remote) on work-life balance, finding no significant difference.
• Hypothesis 3: Concluded that there is no significant difference in the average engagement scores between entry-level and intermediate-level employees.

Conclusions

• Salary: Significant differences exist between experience levels, especially for senior roles.
• Work-Life Balance: Surprisingly, remote work does not significantly affect work-life balance in the sample.
• Engagement: Similar engagement scores were observed across different experience levels, suggesting room for improvement.

🔍 Business Insights & Recommendations

• Salary Structure: There’s a clear gap in salary across experience levels, which should be addressed to ensure fairness and retain top talent.
• Employee Clusters: The three identified clusters suggest a need for tailored approaches. For example, high-performing employees in remote work settings may benefit from additional recognition, while underperforming groups may need enhanced support.
• Remote Work: Though work-life balance ratings were not significantly affected by remote work, other factors such as job satisfaction and professional growth opportunities should be closely monitored for remote workers.