NOTE: The table of contents link in the notebook only works when the notebook is opened with an IDE.
Attrition is the departure of employees from the organization for any reason (voluntary or involuntary), including resignation, termination, death or retirement. Many factors can lead to attrition, this may include, a better offer from another company, natural disasters, relocation of employees etc.
This project aims to answer some questions regarding attrition in an unidentified company. The questions the projects tries to answer includes;
- What are the three main factors behind employee attrition?
- What is the relationship between education and monthly income?
- What is the effect of age on attrition?
- Is income a main factor in employee attrition?
- How does work-life balance impact on employee attrition?
There are two committed files in the repository.
- attr_data.db: The database in which the files are stored.
- factors_affecting_attrition.ipynb: The notebook in which the analysis was done.
There are 36 columns and 1470 rows in the dataset. The columns are;
- Age: Age of employee.
- Attrition: Did an employee leave the company or not?
- BusinessTravel: Do the employee travel for work purposes?
- DailyRate:
- Department: Department employee works.
- DistanceFromHome: Distance of workplace from employee's home.
- Education: Level of education of employee.
- EducationField: Field of study of employee.
- EmployeeCount: Number of employee with this employee number.
- EmployeeNumber: ID number of employee.
- EnvironmentSatisfaction: Environment satisfaction of employee.
- Gender: Gender of employee.
- HourlyRate:
- JobInvolvement: How involved is the employee with his/her work?
- JobLevel: Level of employee.
- JobRole: Employee's job role
- JobSatisfaction: Job satisfaction level.
- MaritalStatus: Employee's marital status.
- MonthlyIncome: Employee's monthly income.
- MonthlyRate
- NumCompaniesWorked: Number of companies employee has worked.
- Over18: Is the employee over 18 years of age?
- OverTime: Does the employee work overtime?
- PercentSalaryHike: Percentage of salary hike.
- PerformanceRating: Performance rating of employee.
- RelationshipSatisfaction: Employee's relationship satisfaction with significant other.
- StandardHours: Working hours in a week.
- StockOptionLevel: Employee stock option.
- TotalWorkingYears: Total number of years an employee has worked.
- TrainingTimesLastYear: Hours spent on training last year.
- WorkLifeBalance: Level of work life balance.
- YearsAtCompany: Number of years at company.
- YearsInCurrentRole: Number of years in current role.
- YearsSinceLastPromotion: Number of years since last promotion.
- YearsWithCurrManager: Number of years with current manager.
This is the notebook used to carry out the analysis. There are 5 sections in the notebook.
This aspect introduces the reader to attrition and some factors that causes attrition. It also summarizes the different columns in the dataset and listed the questions the analysis is trying to answer.
This section of the report contains the sql query to load the data. In this section, the quality of the data was checked by assessing different columns and the preliminary cleaning was carried out.
This section has to do with exploring the data with the sole aim of trying to answer the questions that was posed in the introduction section. The analysis will centre about the question posited at the introduction section.
This aspects deals with the limitations of the analysis.
In this section, the conclusions were made based on the analysis.