Insomnia Detection using Machine Learning Classifiers

The inability to fall asleep, stay asleep, or have non-restorative sleep is known as insomnia. This disorder can significantly lower an individual's quality of life in most poor nations. The study aimed to assess this methodology's efficacy and identify risk factors linked to sleep problems using machine learning techniques. By analyzing a large dataset and employing advanced algorithms, the researchers sought to uncover significant predictors of sleep disabilities and understand the performance of machine learning in this context. In this paper, analysis is done by random forest and LGBM classifiers. The dataset consist of 99,997 participants and their age is between 35-65 years. The comprehensive analysis is also performed and the dataset is fetched from Scopus database.