A data science project to uncover factors that leads to employee attrition
The dataset used in this project is collected from:- https://www.kaggle.com/datasets/pavansubhasht/ibm-hr-analytics-attrition-dataset
Hiring and retaining employees are complex tasks that require capital, time and skills.
'Small business owners spend 40% of their working hours on tasks that do not generate any income such as hiring'.
'Companies spend 15-20% of the employee's salary to recruit a new candidate'.
'An average company loses anywhere between 1% and 2.5% of their total revenue on the time it takes to bring a new hire up to speed.'
Hiring a new employee costs an average of $7645 (Fortune 500 companies)
It takes 52 days on average to fill a position
As a data scientist at a MNC, you are approached by the HR team to develop a model that could predict which employees are most likely to quit the company using the extensive employee data they collected including features like:-
JobInvolvement
Education
JobSatisfaction
PerformanceRating
RelationshipSatisfaction
WorkLifeBalance
Steps Involved
Importing the dataset and checking for missing values and other info regarding variables and their types
Finding hidden patterns in the data using visualisation techniques and statistical analysis
Encoding categorical variables, scaling down the values and splitting the dataset
Common ML models like Logistic Regression, Random Forest and DL based Artificial Neural Network
sahilfaizal0704@gmail.com