Open Access Open Access  Restricted Access Subscription Access

Human Retention using Data Science

Sharayu Kavitkar, Rutuja Powar, Divyesh Patil, Shaila D. Pawar

Abstract


Employees are the backbone of any successful organization and hence employee retention is of utmost importance. Using Data Science, this research work seeks to assist HR and Project Managers in improving the retention rate of valued workers in an organization, thus lowering the company's employee turnover expense. Following extensive research into how to choose the most desirable employee and the application of methodological assumptions, performance was created using conditional logic statements to demonstrate which workers are valuable and which are not. The key goal of this project is to use the K-Nearest Neighbors algorithm and a Decision tree classifier to determine whether or not a company's employee will quit. We use the satisfaction level of an employee, the last evaluation of employee performance, the average monthly hours at work, and the number of years spent in the company, among others, as our features. The dataset was split, using 70% for training the algorithm and 30% for testing it, achieving an accuracy of 95% approximately. HR managers may use this application to make job retention decisions easier.


Keywords


Data Science, Machine Learning, K-Nearest Neighbor (KNN), Decision Tree

Full Text:

PDF

Refbacks

  • There are currently no refbacks.