Volume: 19 Issue-01 (January-June) 2024

---

MENTAL HEALTH PREDICTION FOR EMPLOYEES USING MACHINE LEARNING

ABSTRACT

In today's workplace, addressing mental health challenges is of paramount importance. This project delves into the realm of mental health prediction by harnessing the power of Machine Learning (ML). Utilizing data from a 2014 survey that gauges attitudes toward mental health in the tech industry, the system's primary focus lies in the accurate prediction of mental health consequences within the workplace. Through the implementation of diverse ML algorithms, such as Support Vector Classifier (SVC), Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbours (k-NN), the project assesses the effectiveness of these models in identifying potential mental health risks among employees. With results indicating accuracy rates of 83.59%for SVC, 82.53% for RFC, 74.60% for DT, and 83.33% for k-NN, it becomes evident that machine learning can play a vital role in shaping a more supportive work environment by predicting mental health outcomes. Furthermore, this work paves the way for future enhancements and underscores the significance of algorithm selection and interpretability within the real-world context of organizational mental health support.

FULL TEXT

PDF