DETECTION AND PREVENTION OF WORKFLOW ATTRITION

DETECTION AND PREVENTION OF WORKFLOW ATTRITION

Dr K. Madan Mohan1, Hithishini Mallela2,Manda Akshaya3,Madhagowni Sankalp Goud4,

 Kukuttlapally Koushik5,

1,2,3,4,5 Sreyas Institute of Engineering and Technology1 Assistant Professor (AIML)

ABSTRACT:

Any corporation understands the importance of the workforce in attaining and maintaining a competitive advantage. Workflow attrition rates should be recognized as an interfering element in a business's growth.  Making decisions can play an important role in administration and may indicate the most vital component in the planning process. Attrition is a well-known issue that necessitates sound management decisions in order to retain highly qualified staff. In order to reduce workflow attrition, organizations today have a strong business interest in understanding the factors that contribute to this occurrence. There are several factors leading to the attrition. Predicting employee attrition and determining the key contributors to attrition are thus important organizational goals in order to optimize their human resource strategy. Excitingly, Artificial Intelligence (AI), Machine Learning, and Deep Learning have been actively used, in forecasting attrition probabilities in advance using an automated technique. The goal of this research is to utilize machine and deep learning models and compare them to bring out the highest possible accuracy. We aspire to use Artificial Neural Networks (ANN) and Convolutional Neural Networks(CNN) Algorithms to reach accuracy up to 94%, compared to the previous high of 92%.

Keywords: Workflow Attrition, Predictive model, Deep Learning and Neural Networks, Dataset enhancement