Employee_Attrition

Predicting Employee Attrition And Helping HR’s For Recruitment

Employee turnover (attrition) is a major cost to an organization, and predicting turnover is at the forefront of needs of Human Resources (HR) in many organizations.Organizations face huge costs resulting from employee turnover. Some costs are tangible such as training expenses and the time it takes from when an employee starts to when they become a productive member. However, the most important costs are intangible. Consider what’s lost when a productive employee quits: new product ideas, great project management, or customer relationships.

Our Project concerns a big company that wants to understand why some of their best and most experienced employees are leaving prematurely. The company also wishes to predict which valuable employees will leave next. As well as we also want to help the HR Department in recruiting new employees by predicting his/her attrition rate if he/she is hired as an employee in a particular department.

Let us point out some of the challenges faced by the hiring managers:

Eligible Candidates: Finding and sorting the best candidates on the basis of their resumes.

Demand and Supply ratio: If a selected candidate drops off then again have to repeat the complete process and find a new replacement. Tenuous relationship of hiring manager and recruiters:Sometimes the exact job requirements are not clearly communicated to the hiring managers. According to a survey conducted by ICIMS, 80% of recruiters think they have very good understanding of their job position while 61% of hiring managers believe that recruiters have moderate levels of understanding. This imbalance between both the parties is quite strenuous and creates a barrier for a smooth workflow.

Data Source -: Kaggle Dataset

Link-:https://drive.google.com/open?id=1WXQ1f6uBJTIPCMxfj8Vv2UjHf4adrJ4A

Fields(attributes/features) in the dataset are as follows-:

Name Satisfaction Level Last Evaluation No. Of Projects Avg. Monthly Hours Time Spent In Company Work Accident Left Or Not Promotion Last 5 Years Department Salary Salary Level

Our Project Work

Phase 1 :

Data Analysis

Finding all possible hypothesis

Data Exploration

Data Cleaning if required

Feature Engineering if required.

Data Visualization - Using Tableau Or PowerBi.

Models Building- **Starting with basic models.

Decision Tree

Logistic Regression

SVM

Random Forest etc.

Prediction And Calculating Accuracy , Precision , Recall And F1 Score to decide which model is best.

Phase 2:

Adding more complex features and using deep learning using TensorFlow building a final model and Developing a pickle file.

Prediction And Calculating Accuracy , Precision , Recall And F1 Score.

Final Story and Full Analysis of the Outcomes Using PowerBi .

Reasearch Paper : Early Prediction of Employee Attrition using Data Mining

IEEE Link -: https://ieeexplore.ieee.org/document/8692137

Research Gate -: https://www.researchgate.net/publication/332528099_Early_Prediction_of_Employee_Attrition_using_Data_Mining_Techniques

Youtube Video Link : https://youtu.be/sH5Hwwu_8kM