Psychological health is a crucial part of people’s lives and society. Poor mental health affects our well-being, our ability to work, and our connotations with friends, family, and community. There are many different types of mental illness, sometimes referred to as mental disorders with different causes, symptoms, and treatments. Early detection of mental health problems allows specialists to treat them more effectively and it improves patient's quality of life. Mental disorders are diagnosed and classified based on the symptoms and behavioural changes of the person. A few previous studies assessed machine learning techniques to detect mental health issues using several accuracy criteria. This study evaluated machine learning models logistic regression, random forest, naïve bayes, decision tree, k-nearest neighbor, neural network and ensemble machine learning to classify whether the persons working in tech industry suffered from mental illness or not, and compared their efficacy using accuracy, precision, recall and F1 score metrics. This study tested these machine learning models for classifying mental disorder data and found that ensemble learning classifier achieved best accuracy of 84.5%, precision of 0.80, recall of 0.91 and f1-score of 0.85.