Abstract:
"This research focuses on automating the process of identifying mental distress among finance professionals in Sri Lanka using machine learning techniques. The objective is to develop an automated system that can detect signs of mental distress early, enabling timely intervention and support from mental health professionals. Despite the pivotal role finance professionals play in the Sri Lankan economy, there is a notable gap in research regarding the impact of mental stress on this specific group, particularly during economic crises. This study aims to fill this gap by predicting mental distress among finance professionals during periods of crisis using machine learning models.
The primary objectives of this study are twofold: first, to explore and harness the potential of machine learning in predicting mental distress among finance professionals during crisis
periods; and second, to use various machine learning algorithms to forecast the likelihood of mental distress based on diverse variables.
Several machine learning algorithms were employed in this study, including Logistic
Regression, Naïve Bayes, Decision Trees, Random Forest, Gradient Boosting, and Support
Vector Machines (SVM). Among these, the SVM model emerged as the most effective for
predicting mental distress among finance professionals.
The dataset comprised responses from 387 finance professionals collected through a survey, categorizing this study as qualitative research. By identifying the predictors of mental distress, this research provides valuable insights into the challenges faced by finance professionals during economic crises, thereby laying the groundwork for the development of targeted interventions aimed at mitigating mental distress within this population."
