Machine Learning based Employee Attrition Predicting
Subhani Shaik *
Jawaharlal Nehru Technological University Hyderabad, Hyderabad, Telangana, India.
P. Santhosh Kumar
Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad, Telangana, India.
S. Vikram Reddy
Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad, Telangana, India.
K. Sai Srinivas Reddy
Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad, Telangana, India.
Sunil Bhutada
Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad, Telangana, India.
*Author to whom correspondence should be addressed.
Abstract
Now a day’s variety of reasons for job resignations due to this, we have to take different types of measurements for prediction of job seekers. They have different reasons for not doing jobs well and fell like pressure. Many employees suddenly come to an end of their service without any reason. Techniques of machine learning have full-grown in fame in the middle of researchers in current years. It is accomplished of propose answer to a broad range of problems. Help of machine learning, you may produce prediction concerning staff abrasion. So machine learning model we will be using TCS employee attrition a genuine time dataset to train our model. The aim of this study is to at hand a comparison of different machine learning algorithms for predict which employees are probable to go away their society. We propose two methods to crack the dataset into train and test data: the 75 percent train 25 percent test split and the K Fold methods. Three techniques are three methods that we employ to train our model for correctness comparison, and we will compare the exactness of the models generate using these three Boosting Algorithms.
Keywords: Machine learning, gradient boosting algorithms, K-Fold methods, light GBM boost, XG boost