Envisaging Employee Churn Using MCDM and Machine Learning

Employee categorisation differentiates valuable employees as eighty per cent of profit comes from twenty employees. Also, retention all is quite challenging and incur a cost. Previous studies have focused on employee churn analysis using various machine learning algorithms but missed the an based accomplishments. This paper provides approach categorising to quantify importance multi-criteria decision making (MCDM) techniques, i.e., criteria through inter-criteria correlation (CRITIC) assign relative weights accomplishments fuzzy Measurement Alternatives Ranking according Compromise Solution (MARCOS) method divide into three categories. Followed by executing each category original dataset investigate categorisation. CatBoost, Support Vector Machine, Decision Tree, Random Forest XGradient Boost been used analyse categorised non-categorised accuracy, precision, recall Mathew's Correlation Coefficient (MCC) derive best suitable algorithm for dataset. CatBoost showed results regarding performance measurements are better than datasets.