Breaking Down the Breakaway: How Age, Tenure, and Income Shape Attrition Patterns

When I first got the chance to explore human resources data, I was both excited and a little nervous. Imagine stepping into the shoes of a People Data Analyst intern for a big company like IBM and trying to figure out why so many employees were leaving. It felt like I was on a treasure hunt, searching for clues hidden within numbers. Sometimes the clues were obvious, and other times, they surprised me in unexpected ways.

Why THIS Project?

I chose this project because I’ve always been fascinated by how different factors can influence people’s decisions at work. Employee attrition is a big topic, especially in today's job market where many people change jobs frequently. I found it intriguing to see if I could pinpoint specific reasons behind why employees were leaving and how characteristics like age, experience, and income played a role in that decision.

What Readers Will Gain

In this article, you’ll learn about the patterns I discovered regarding employee attrition as well as how age and total working years relate to monthly income. I’ll share insights from my analysis and what those findings could mean for companies looking to keep their employees happy and engaged.

Key Takeaways

• Monthly income is more influenced by total working years than age.

• Younger employees are more likely to leave than older ones.

• There isn’t a significant difference in attrition rates between newer employees and those with more experience at the company.

Dataset Details

The dataset I used comes from IBM and is available on Kaggle. It includes 1,470 entries with 35 different attributes, such as Attrition, Age, Monthly Income, and Total Working Years. While it may not be real-world data, it provided a solid foundation for analyzing trends and making observations about employees.

Analysis Process

To start my analysis, I checked the data to ensure there were no errors or inconsistencies. I applied linear regression to explore the relationships between variables like Monthly Income and Age, and Total Working Years. I was surprised to find that age only accounted for about 25% of the variance in monthly income, while total working years accounted for around 60%. This got me thinking—people’s career paths can vary greatly. Some might take breaks or switch industries, which can affect their income.

Visuals and Insights

1. Scatterplot Matrix: This visual helped show the relationship between age and monthly income. The clustering of dots between ages 40 and 60 in the first scatterplot revealed that income levels can differ significantly for people in that age group. This suggests that while age is a factor, it’s not the only one influencing income.

   

   

   

   Linear regression

   

   Age only accounts for about 25% of the variance in Monthly Income.

   

   Linear Regression

   

   Total Working Years accounts for about 60% of the variance in Monthly Income

2. Boxplot: This analysis indicated that those who left the company were generally younger than those who chose to stay. Younger employees may be more likely to explore different job opportunities, seeking new experiences more frequently than older, more stable employees.

   

   

   Employees who left were younger than those who stayed

   

   Welch Two Sample t-test

   

   The p-value is less than 0.05, showing that the difference is ages is statistically significant.

3. Welch Two Sample t-test: This test clarified that no significant difference exists between newer employees and those who have been with the company longer. This finding challenges the assumption that tenure directly affects attrition.

   

   Welch Two Sample t-test

   

   The p-value is greater than 0.05, showing that the difference in employee number is not statistically significant.

   
   

Main Takeaways

My findings suggest that companies might need to offer more incentives to keep younger workers engaged if they want to prioritize retention. Additionally, hiring employees with fewer years of experience (independent of age) could be a cost-effective strategy, as they tend to have lower salary demands, but this approach also requires thoughtful consideration of the company’s culture and goals.

Conclusion and Personal Reflections

This project taught me a lot about the complex factors influencing employee attrition. I faced challenges, especially in interpreting the data correctly. However, this experience has shaped my perspective on how important it is for businesses to understand their workforce's dynamics. Moving forward, I feel more motivated to explore HR analytics further, as it has opened my eyes to the power of data in shaping workplace strategies.

Call to Action

I would love to hear your thoughts! Please connect with me on LinkedIn, or leave a comment with any questions or insights you might have.