RETAINPRISM - A Predictive approach to Manage Voluntary Employee Turnover

Abstract

Employees are considered as a vital aspect in any organization. Operating with the proper, efficient and skilled workforce is of paramount importance when sustaining in the highly competitive business environment. Therefore, retention of skilled employees within the organization is of key importance. Employee turnover is regarded as the percentage of employees that leave an organization. Many claim that is it a leak of human capital from a company. Existence of high turnover rates within an organization could be detrimental for the longevity of the company. It can cause an organization to bear both direct and indirect costs. In comparison to various industrial fields, the IT sector has a considerable higher employee turnover rate owing to its highly lucrative nature. This dissertation aims to analyze current and past data related to employee turnover in the IT industry, design, develop and evaluate a prediction model that will predict the employee turnover and provide valuable insights which will allow the organization to take remedial actions beforehand to manage and reduce the employee turnover rate within the organization. Furthermore, it will concentrate on distinguishing the proper cause of employee turnover and will aid the company to come up with a proper retention strategy or a succession plan that will aid in tackling the pertaining problem. An extensive research was conducted prior to formulating the conceptual framework that clearly captures and addresses the pain points identified in the current context. Based on the research conducted, the main turnover drivers that affect the psyche of the employees and influence the turnover behavior were identified as lack of compensation and rewards, lack of job satisfaction, lack of development and growth opportunities and poor employer employee relationships. The prepared dissertation aims to identify and address these issues and provide retention strategies to mitigate the risk, with the use of HR analytics which focus on using machine learning capabilities and data mining techniques to solve widespread HR problems.