Unlocking Insights: Understanding the Workforce Landscape
Olubiyi Tolulope George
Human Resources Data Administrator | SPHRi, Analytics
I am delighted to share the results of a comprehensive data analysis project offering valuable insights into the broader workforce and job market. We explored key trends and patterns that shape the employment landscape using advanced analytics and the powerful R programming language.
Join me on this enlightening journey as we unravel the intricacies of the workforce and gain valuable knowledge to drive success in any organization.
Data Overview:
Our analysis covered a diverse dataset with 19,104 observations and 13 variables, providing a rich source of information about employees in various industries. With variables including age, gender, education level, salary, tenure, designation history, performance ratings, and more, we gained a holistic view of the workforce dynamics.
Data Cleaning:
To ensure the accuracy of our analysis, we meticulously cleaned the dataset. This involved standardizing date formats, transforming categorical variables into numerical representations and preparing the data for in-depth exploration.
Exploratory Data Analysis:
Our in-depth analysis uncovered crucial insights that shed light on the broader workforce landscape:
1.?????Age Distribution: Employees’ ages span a wide range across industries, from early twenties to late fifties. Understanding the generational composition of the workforce is vital for tailoring HR policies, fostering collaboration across generations, and embracing the diversity of ideas and perspectives.
2.?????Gender Diversity: A balanced gender distribution is a crucial characteristic of today's workforce. Our analysis revealed approximately 58% male and 42% female representation, showcasing the progress in creating inclusive work environments where everyone has equal opportunities to thrive.
3.?????Education Levels: The education backgrounds of employees vary, with individuals holding college, bachelor's, and master's degrees. This diverse educational spectrum highlights the different skill sets and knowledge contributing to workforce capabilities.
4.?????Salary Distribution: Analyzing salary ranges across industries provides valuable insights into compensation trends and market competitiveness. Our analysis revealed a broad salary spectrum, with average salaries ranging from $10,747 to $188,418, helping organizations evaluate their compensation strategies and attract top talent.
Prediction Models:
In addition to descriptive analysis, we developed advanced prediction models to gain a deeper understanding of workforce dynamics:
1.?????Logistic Regression Model: By leveraging logistic regression, we successfully predicted attrition rates based on various factors, including age, gender, education level, salary, tenure, and performance ratings. These insights allow organizations to identify potential risk factors and take proactive measures to retain valuable talent.
a.?????Some notable findings from the model include:
i.????Every increase in age increases the odds of resignation by 1%.
ii.????For every increase in an employee's salary, the odds of not resigning increase by 500%.
领英推荐
iii.????For every increase in the joining designation, the odds of not resigning increase by 17%. The higher an employee’s designation when joining an organization, the longer they are likely to stay.
iv.????For every increase in total business value the employee generates, the odds of not resigning increase by 200%. Employees are happier and better engaged when they can measure their achievements.
v.????For every increase in quarterly performance rating, the odds of not resigning increase by 76%. Employees are less likely to leave an organization where their contributions are recognized and rewarded.
2.?????Decision Tree Model: Using decision trees, we uncovered significant conditions that contribute to excellent quarterly performance across industries. This valuable knowledge empowers organizations to focus on critical factors that drive employee success and create an environment conducive to high performance.
The decision tree output provides a visual representation of the decision-making process of a model. It helps interpret how the model uses input features to make predictions or classify instances.
In summary, the tree agrees with the findings in our analysis using logistic regression. The tree shows the three key factors that drive employee performance are:
1.????Total business value generated by the employee.
2.????Designation as of their joining date.
3.????Salaries.
3.?????Salary Forecasting: We forecasted the mean salary trends in the job market over the next twelve months by applying advanced time series analysis. This information equips organizations with the foresight to adjust their compensation strategies and remain competitive in attracting and retaining top talent.
The forecast indicates a relatively stable trend in the mean salary over the next twelve months, with a slight downward trajectory.
Call To Action
Our analysis of workforce trends in the job market has uncovered a critical issue that demands immediate attention. The findings reveal a concerning relationship between salary, average age, and employee performance.
As average salaries have declined, so have both age and quarterly performance ratings, leading to a loss of experienced professionals and impacting overall organizational performance.
To tackle this challenge head-on, we strongly recommend two key actions:
1.?????Benchmark Industry Pay Structure: We can ensure our salaries remain competitive by assessing industry standards. Identifying gaps will help us attract and retain highly skilled employees in today's job market.
2.?????Review Salary and Compensation Policies: A comprehensive review will effectively align our policies with market trends and reward performance and experience. This includes salary scales, bonuses, incentives, and benefits.