Detection and Prevention of Workflow Attrition

Each business acknowledges the importance of employees in building and sustaining competitive advantage. The turnover of employees should, therefore, be seen as something that negatively affects business growth. It is in this process that sound decisions are made regarding management. Its role may very well be of utmost importance in any planning prepared. Worker turnover has been a known factor, and decisions in management call for sound judgment to retain better employees. Today's firms have a significant interest in finding the causes and circumstances behind employee turnover to enable its reduction. Some causes contribute to instability. In this manner, predicting the likelihood of employee turnover and primarily identifying causes of turnover are vital organizational objectives to optimize HR techniques. Interests, artificial intelligence (AI), machine learning, and deep learning have been actively applied to anticipate instability likelihood using automated techniques. This paper aims to utilize machine learning and deep learning models and compare them to attain the highest possible accuracy. We intend to achieve an accuracy of 94%, which is higher than the previous best of 92%, using the ANN and CNN algorithms.