Hiring Process Analytics

By Vivek Dhande
 PROJECT DESCRIPTION
• Our task is to analyze the company's hiring process data and draw meaningful
insights from it. The hiring process is a crucial function of any company, and
understanding trends such as the number of rejections, interviews, job types,
and vacancies can provide valuable insights for the hiring department.
 APPROACH:
1. Clean the data by removing duplicates and irrelevant entries, ensuring it's properly
formatted.
2. Identify and remove any outliers that could significantly impact the analysis.

3. Perform descriptive statistics to gain a general understanding of the dataset.

4. Extract useful insights through statistical analysis and visualize them using data
visualization methods.
Tech Stack
• MS-Excel
Excel Sheet Hyperlink
• https://docs.google.com/spreadsheets/d/1uNVJkCx0Ci43AbO_-E-
J_g4m7czMibec/edit?usp=sharing&ouid=108219561685363950349&rtpof=true&sd
=true
 Data Cleaning
➢ Handling Missing Values
1. The column "event_name" contains 15 rows with "-" as their values. These can be considered null values. We replaced
them with "Don't want to reveal" since both imply the same meaning in the context of this project, indicating that the
gender of the candidate is unknown.
 Data Cleaning
➢ Handling Missing Values
2. In the "Offered Salary" column, one row had a null value. The corresponding "Department" is "Sales Department" and
the "Post Name" is "i7". We replaced the null value with the median salary for the Sales Department with the "i7" Post
Name, which is 49,628

Median Formula applied on that

 Data Cleaning
➢ Handling Missing Values
3. The "Post Name" column has one row with "-" as its value, indicating a null value. The corresponding "Department" is
"Sales Department" and the "Offered Salary" is 85,914. We replaced the null value with the most common post for
candidates in the Sales Department with offered salaries between 85,000 and 96,000, which is "c9".
 Data Cleaning
➢ Handling Missing Values
4. Column Post Name has a category “c-10” which seems to be a typo and the correct category should be “c10” which
we rectified.
 Data Cleaning
➢ Detecting and Removing Outliers
1 . From the below Box Plot of Column Offered Salary, we can see that there are three rows whose Column values are
outliers and the values are 200000, 300000, 400000. We can replace them with median value of Offered Salary for
corresponding Department and Post Name
➢ Detecting and Removing Outliers
Data Cleaning
➢ Identifying Duplicate Values in
application_id

The "application_id" column contains 76 rows with duplicate values. These should either be removed or corrected. For
now, we are simply highlighting the cells with duplicate values.
 A. Hiring Analysis: The hiring process involves bringing new individuals into the organization for various roles.
Task: Determine the gender distribution of hires. How many males and females have been hired by the company?

Result: • Currently, more than half of the hired

candidates are male, with only 39.51%
being female and the remainder not
disclosing their gender. A high gender
ratio skewed towards males can
potentially tarnish the organization's
public image. To address this, the
organization should prioritize
reducing the gender ratio to achieve a
balance closer to parity.]

• The Data Quality Team needs to

rigorously ensure that all data is
complete and relevant. Incomplete or
irrelevant data could significantly
impair the analysis process.
B. Salary Analysis: The average salary is calculated by adding up the salaries of a group of employees and then dividing the total
by the number of employees.
Task: What is the average salary offered by this company? Use Excel functions to calculate this.

Result:
Average Offered Salary :

Insight:
The average offered salary is Currency-Unit 49,878.86,
while the average salary of hired candidates stands at
Currency-Unit 49,594.91. This closeness indicates that the
hiring team is recruiting candidates within the
organization's predetermined salary bands."
 C. Salary Distribution: Class intervals represent ranges of values, in this case, salary ranges. The class interval is the
difference between the upper and lower limits of a class.
Task: Create class intervals for the salaries in the company. This will help you understand the salary distribution.

Result:
 C. Salary Distribution: Class intervals represent ranges of values, in this case, salary ranges. The class interval is the
difference between the upper and lower limits of a class.
Task: Create class intervals for the salaries in the company. This will help you understand the salary distribution.

Insight:
• We observe that the maximum offered salary falls within the range of Currency-Unit 40,001-50,000, while the minimum offered
salaries are in the intervals of Currency-Unit 9,001-10,000 and Currency-Unit 90,001-100,000. This suggests that there were more
job openings for mid-level experience positions compared to senior-level or entry-level positions, assuming salary correlates with
work experience.
• Similarly, the distribution of salaries among hired candidates also reflects this trend, with the majority hired for middle-level
experience positions and fewer for senior-level or entry-level positions, assuming that salary correlates with work experience
 D. Departmental Analysis: Visualizing data through charts and plots is a crucial part of data analysis.
Task: Use a pie chart, bar graph, or any other suitable visualization to show the proportion of people working in
different departments

Result:

Insight:
• From the above pie chart, we can observe that most candidates are hired in Operations Department followed by Services
Department and Sales Department and the least candidates are hired in Human Resource Department.

• These numbers may indicate the size of teams and importance of the departments in the organization.
 E. Position Tier Analysis: Different positions within a company often have different tiers or levels.
Task: Use a chart or graph to represent the different position tiers within the company. This will help you
understand the distribution of positions across different tiers.

Result:

Insight:
• Here, we can observe that the organization has hired most candidates for post tier c9 followed by c5 and then i7 at distant third.
Conclusion
• This project has underscored the critical role of data analytics in the hiring process
of organizations. It has provided valuable insights such as rejection rates, reasons
for rejections, applicant profiles, vacancy trends, and more, enabling the hiring
department to make informed, data-driven decisions.
• Throughout this project, I gained insights into various aspects, including the
gender distribution among hired candidates, the comparison between average
offered salary and average hired salary, the distribution of salaries for offered
positions versus hired candidates, and the departmental and hierarchical
distribution of hired candidates. Additionally, I acquired hands-on experience in
data preprocessing, particularly in data cleaning, which was necessary to ensure
data accuracy and reliability.