Employee attrition is one of the most important factors for any company to get benefits because it has a muscular impact and hampers the organization’s long-term growth strategies. For employee attrition, an organization loses its valuable skills and experience, which is why organizations try to keep their employees in order to minimize the cost of training and recruitment. An organization can avoid the stressful and unfair manual prediction process by utilizing machine learning approaches that predict the likelihood of attrition based on employee attributes. This paper proposed an approach which enables an organization to find out the risk factor for employee attrition. In the preprocessing part, the dataset will be balanced using Borderline-SMOTE Technique, and after that, the linear discriminant analysis technique used to reduce the dimension. Then AdaBoost algorithm is performed on this dataset to get a perfect score. The method claims 93.75% accuracy. In this paper, explainable artificial intelligence (XAI) is used to improve model prediction transparency, interpretation, and trustworthiness. This paper explained the AdaBoost algorithm using XAI techniques including SHapley Additive Values(SHAP). The effort intends to precisely determine the employee by means of an automated screening system including ML methods with capacity for explanations.