ABSTRACT An industry or firm can not imagine without em-
ployees. Employee attrition refers to that event when
an employee quits the organization. Industry suffer-
ers considerably when an employee leaves the firm for
personal or professional reasons. During this time,
the company wastes additional time and resources
on new recruitment and training processes. In ad-
dition, the company's ongoing tasks become increas-
ingly difficult to complete on schedule. Therefore,
when the voluntary attrition rate is high, the com-
pany will experience significant financial and other
difficulties. Under these situations, the Human Re-
source (HR) department's first priority is to reduce
the turnover rate. From this perspective, further
study has been conducted through the use of statis-
tical analysis and various machine learning and data
mining approaches, such as Extreme Gradient Boost-
ing, Random Forest, Naive Bayes, decision trees, etc.
This paper has applied a cutting-edge boosting tech-
nique, CatBoost, with a feature engineering process
to detect and analyze employee turnover. Our detec-
tion technology outperforms all other technologies on
the industry and identifies the key causes of attrition.