Explainable AI for Predictive Analytics on Employee Attrition

Employees are the key to an organization's success. An employee can directly affect the productivity of any organization. Hence, retention of the employees becomes great challenge for every organization. Artificial Intelligence is extensively used in such cases to analyze the problem behind a company's low retention rate of valuable employees. The analysis can help organizations to build up strategies to deal with the problems of employees leaving an organization. The current work aims to detect key features or main reasons behind an employee's key decision to stay or leave the organization. Primarily in this work machine learning is used extensively to create a create a prediction model on the collected data from human resources of different organization. In addition, the proposed framework uses explainable Artificial Intelligence methods such as SHAPley Additive exPlanations and Local Interpretable Model-Agnostic Explanations to analyze the key factors behind employees leaving the organizations. The current work managed to accurately create a prediction model with a score of 96% and detect three key features behind employee's decision of staying or leaving any organization.