Scribd
Upload
18 views

HR Data Analysis

Data analysis report

Uploaded by

1js21ec041
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
18 views

HR Data Analysis

Data analysis report

Uploaded by

1js21ec041
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

HR Data Analysis

1. Introduction

This project analyzes an HR dataset to uncover insights about employee demographics,


performance, engagement, and other key HR metrics. Using Python libraries like pandas and
matplotlib, the analysis offers actionable insights for better workforce management and decision-
making.

2. Objectives

 Analyze gender, race, and marital status distributions.


 Investigate salary trends across different attributes such as gender, department, and
employment status.
 Explore employee performance, satisfaction, tenure, and recruitment effectiveness.
 Examine termination trends and their reasons.

3. Dataset Overview

The dataset contains HR-related attributes, including:

 Demographics: Gender, race, marital status.


 Job Details: Department, salary, hire date, termination date.
 Performance Metrics: Engagement survey, satisfaction score, performance score.
 Other Metrics: Absences, special project counts, recruitment source.

4. Analysis and Insights

4.1. Data Exploration

python

print(df.head()) # Display first few rows


print(df.isnull().sum()) # Check for missing values
print(df.describe()) # Summary statistics

 Insights:
o Missing values in certain columns like termination date (for active employees).
o Basic summary statistics highlight salary ranges and other key metrics.
4.2. Demographic Analysis

 Gender Distribution:

python

gender_distribution = df['Sex'].value_counts()

 Identifies the male-to-female ratio in the organization.


 Race Distribution:

python

race_distribution = df['RaceDesc'].value_counts()

 Examines diversity in the workforce.


 Marital Status Distribution:

python

marital_status_distribution = df['MaritalDesc'].value_counts()

 Highlights proportions of married, single, and other marital statuses.

4.3. Salary Analysis

 Salary by Gender:

python

salary_by_gender = df.groupby('Sex')['Salary'].mean()

 Average salary comparison between genders.


 Salary by Department:

python

salary_by_department = df.groupby('Department')['Salary'].mean()

 Shows salary trends across various departments.


 Salary by Race:

python

salary_by_race = df.groupby('RaceDesc')['Salary'].mean()

 Reveals potential disparities or trends in salaries by race.


4.4. Performance and Satisfaction

 Performance-Satisfaction Correlation:

python

performance_satisfaction_correlation = df[['EngagementSurvey', 'EmpSatisfaction']].corr()

 Explores whether higher engagement correlates with better satisfaction.


 Absences vs. Performance:

python

absences_by_performance = df.groupby('PerformanceScore')['Absences'].mean()

 Identifies whether more absences affect performance scores.

4.5. Termination Analysis

 Termination Rates:
python

termination_rate = df['EmploymentStatus'].value_counts()

 Shows the proportion of active versus terminated employees.


Termination Reasons:

python

terminated_employees = df[df['EmploymentStatus'] != 'Active']


termination_reasons = terminated_employees['TermReason'].value_counts()

 Analyzes reasons for employee termination.


4.6. Recruitment Effectiveness

 Recruitment Source Distribution:

python

recruitment_source_dist = df['RecruitmentSource'].value_counts()

 Highlights the most common recruitment sources.


 Recruitment Source vs Performance:

python

recruitment_performance = df.groupby('RecruitmentSource')['PerformanceScore'].value_counts()
 Assesses whether certain recruitment sources yield better-performing employees.

4.7. Special Projects

python

projects_by_department = df.groupby('Department')['SpecialProjectsCount'].mean()

 Average number of special projects handled by employees in different departments.


5. Visualizations

The following charts were created to enhance the analysis:

1. Bar Chart: Gender distribution and salary by gender.


2. Pie Chart: Salary by department, race, and employment status.
3. Line Chart: Termination rates over time.
4. Histogram: Salary and satisfaction distributions.
5. Scatter Plot: Performance vs engagement satisfaction.
6. Bar Chart: Recruitment source performance.

6. Insights and Recommendations

Demographics:

 Male and female employees have similar average salaries, but deeper analysis may be
needed to uncover inequities.
 Race and marital status distributions suggest potential diversity and inclusion
opportunities.

Salaries:

 Salary differences between departments highlight priority or high-revenue roles.


 A clear salary disparity exists across employment statuses and races, which should be
investigated further.

Performance and Satisfaction:

 A positive correlation between engagement and satisfaction emphasizes the importance


of employee engagement initiatives.
 Employees with higher performance scores tend to have fewer absences.

Terminations:

 Majority of terminated employees cite specific reasons, such as performance issues or


restructuring.
 Insights into tenure by department suggest opportunities to increase retention rates.

Recruitment:

 Recruitment source effectiveness is evident, with some channels yielding better-


performing employees. Focusing on high-performing sources could improve hiring
quality.

Projects:

 Departments handling fewer special projects may indicate under-utilization or varying


job scopes.

7. Conclusion

The analysis provides valuable insights into HR data, addressing key areas like salaries,
performance, terminations, and recruitment. By implementing the recommendations,
organizations can enhance employee satisfaction, reduce turnover, and optimize hiring strategies.

You might also like