Predicting Employees under Stress for Pre-emptive Remediation using Machine learning Algorithm

Abstract

With the ongoing COVID-19 pandemic, businesses and organizations have acclimated to unconventional and different working ways and patterns, like working from home, working with limited employees at office premises. With the new normal here to stay for the recent future, employees have also adapted to different working environments and customs, which has also resulted in psychological stress and lethargy for many, as they adapt to the new normal and adjust their personal and professional lives. In this work, data visualization techniques and machine learning algorithms have been used to predict employees stress levels. Based on data, we can develop a model that will assist to predict if an employee is likely to be under stress or not. Here, the XGB classifier is used for the prediction process and the results are presented showing that the method facilitates getting a more reliable model performance. After performing interpretation utilizing XGB classifier it is determined that working hours, workload, age, and, role ambiguity have a significant and negative influence on employee performance. The additional factors do not hold much significance when associated to the above discussed. Therefore, It is concluded that concluded that increasing working hours, role ambiguity, the workload would diminish employee representation in all perspectives.

A Feasibility Study for Applying Explainable Predictive Models for the Detection of Mental Health Conditions

“…2. The results give new suggestions to improve workplaces in terms of improving the Mental Health of their employees, which are not covered by sources such as [15], where role ambiguity, age and working hours were the influential critical factors found affecting Mental Health. Our study finds that the ease of leave accessibility, how supportive companies are to Mental Health concerns, and the overall importance companies place on Mental Health were all key factors influencing employees' Mental Health.…”

“…and the associated modified working conditions, a problem bearing great relevance to the present day. Specifically, they utilize an XGBoost Classifier to obtain a relatively high F1-score (see section 4.4 for an explanation of this metric) of 0.82 [15]. Their feature importance analysis found that working hours, age, and role ambiguity had the most significant negative impact on employee performance.…”

“…The following Machine Learning algorithms were chosen: Logistic Regression, Gradient Boosted Machines (GBM), Extreme Gradient Boosting (XGBoost) and Random Forest. Predictive performance along with ease of interpretability was considered in the choice of these models: all four of these models are ideally suited to a classification setting in terms of their predictive power, while Logistic Regression has the advantage of high ease of interpretability [15]. Logistic…”

Metaheuristic optimization based feature subset selection with deep belief network for stress prediction in working employees

“…With the improvement of big data analytics, technology starts concentrating on disease prognosis from the perspective of big data analysis 8 . Several researches were carried out for selecting the property automatically from various data, for improving the performance of the risk classification, instead of formerly‐selected features 9 . Therefore, in the last few years, several studies focused heavily on convolution neural networks (CNNs), logistic regression (LR), support vector machines (SVMs), machine on machine learning‐based disease prognosis (ML), 10 and so on.…”

“…8 Several researches were carried out for selecting the property automatically from various data, for improving the performance of the risk classification, instead of formerly-selected features. 9 Therefore, in the last few years, several studies focused heavily on convolution neural networks (CNNs), logistic regression (LR), support vector machines (SVMs), machine on machine learning-based disease prognosis (ML), 10 and so on. During the testing process, input information is categorized into different classes.…”