An Experimental Analysis of Work-Life Balance Among The Employees using Machine Learning Classifiers

TL;DR

This paper explores using machine learning classifiers to analyze and predict factors affecting work-life balance among employees, achieving up to 71.5% accuracy with Random Forest, SVM, and Naive Bayes algorithms.

Contribution

It introduces an empirical approach applying ML classifiers to predict work-life balance factors using a large dataset of employees.

Findings

Random Forest achieved 71.5% accuracy in predicting WLB.

Certain factors significantly influence employees' work-life balance.

ML algorithms can effectively model work-life balance dynamics.

Abstract

Researchers today have found out the importance of Artificial Intelligence, and Machine Learning in our daily lives, as well as they can be used to improve the quality of our lives as well as the cities and nations alike. An example of this is that it is currently speculated that ML can provide ways to relieve workers as it can predict effective working schedules and patterns which increase the efficiency of the workers. Ultimately this is leading to a Work-Life Balance for the workers. But how is this possible? It is practically possible with the Machine Learning algorithms to predict, calculate the factors affecting the feelings of the worker's work-life balance. In order to actually do this, a sizeable amount of 12,756 people's data has been taken under consideration. Upon analysing the data and calculating under various factors, we have found out the correlation of various factors and WLB(Work-Life Balance in short). There are some factors that have to be taken into serious consideration as they play a major role in WLB. We have trained 80% of our data with Random Forest Classifier, SVM and Naive Bayes algorithms. Upon testing, the algorithms predict the WLB with 71.5% as the best accuracy.