An Ensemble based Approach for Prediction of Happiness Index for School Children

The well-being and happiness of students play a vital role in schools. The mental well-being of school children is a critical aspect of their overall development, influencing academic performance, social interactions, and long-term mental health. This study focuses on measurement of happiness index in school incorporating self-assessment facility with a special emphasis on mental health. The proposed model leverages a dataset comprising various socio-demographic, academic, psychological and physiological features collected from a diverse group of school children. Features such as academic performance, extracurricular involvement, peer relationships, and family dynamics will be considered as input variables. The target variable is the happiness index, measured through surveys and self-assessment tools designed for children. Ensemble model containing machine learning algorithms such as KNN, Naïve Bayes, XG boost is used to predict the happiness index of school children. After measurement of their happiness if their value is below than a threshold value then a suggestion report is sent to their email id. This study helps both schools, parents and educators to take actionable insights for improvement and promote the well-being of school students.