Classification of Sleep Disorders Using Random Forest on Sleep Health and Lifestyle Dataset

Abstract

This study aims to classify sleep disorders using Random Forest method on the Sleep Health and Lifestyle
dataset. This dataset contains information about sleep, lifestyle, and relevant health factors. In this study, the
dataset was processed and divided into training and testing subsets. The Random Forest model was trained using
the training subset with sleep and health-related features. The split quality in each decision tree was
measured using the Gini Index. The model was evaluated using the testing subset to measure its accuracy and
classification performance. The evaluation results showed that the Random Forest model could accurately predict sleep disorders. Analysis of class distributions, correlation relationships between features,
and visualization by gender provided insights into the factors that influence sleep disorders. This research can potentially contribute to the field of health and medicine, especially in the recognition and diagnosis of sleep
disorders.