Applied Research

MACHINE LEARNING APPROACH FOR MODELING PREDICTION OF HUMAN ERRORS DUE TO STRESS BASED ON WORK ENVIRONMENT AND JOB DEMANDS

---

Abstract

Previous research has elucidated the prediction of human errors through the integration of eye tracking and machine learning methods.  However, work-related stress can directly influence human errors due to the environment and job demands. In addition, the methods applied in previous studies were limited to computer-based tasks only. This research utilizes direct measurements of the human body and the environment, thereby not being limited to specific types of work only. The aim of this study is to develop a predictive model for human error occurrence due to stress based on the work environment and job demands, using a classification algorithm approach in machine learning. Machine learning algorithms such as Random Forests and Decision Trees are applied to classify the occurrence of human errors. The research process begins with collecting a dataset, data preprocessing, modeling, and evaluation. The results show that both algorithms achieve a model accuracy of > 90%. However, the Random Forest algorithm exhibits the highest accuracy and recall compared to the Decision Tree algorithm. Therefore, this research recommends the use of the Random Forest algorithm for modeling human error prediction.

Keywords: Stress, Work Environment, Job Demand, Human Error, Machine Learning

How to Cite:

Dahlan, M. R. & Wahyuning, C. S., (2025) “MACHINE LEARNING APPROACH FOR MODELING PREDICTION OF HUMAN ERRORS DUE TO STRESS BASED ON WORK ENVIRONMENT AND JOB DEMANDS”, The Journal of Technology, Management, and Applied Engineering 1(1). doi: https://doi.org/10.31274/jtmae.16882