Exploring potential predictors of psychological distress among employees: A Generalized ARC-GRU Based Model

It seems to have an increase in employee reports of psychological distress across a wide range of industries. Research from the past indicates that a significant portion of the global workforce has dealt with emotional and mental health challenges. The worker's physical, social, and occupational functioning could be negatively impacted if these concerns are not addressed sooner. The three steps that make up this suggested approach are preprocessing, feature extraction, and model training. Factorization is a part of data preprocessing that involves encoding input values into categorical variables, which are also known as enumerated types. Data visualization, training speed, accuracy, and overfitting prevention are all enhanced by feature extraction. In order to train the model, a Generalized ARC-GRU was utilized. Traditional methods, such as GRU and GARC, are surpassed by the suggested methodology. After applying the method, the accuracy increased by 91.48 percent.