Predictive Sleep Disorder Modelling: Using Machine Learning with Lifestyle and Sleep Health Data

The Sleep Health and Lifestyle dataset was analyzed using different Machine Learning (ML) techniques in the study. The dataset contains information about a variety of sleeping patterns, health concerns, and lifestyle choices. The study incorporated various classification algorithms, including Light Gradient Boosting Machine (LGBM), AdaBoost, Random Forest (RF), Extra Trees, k-Neighbours Networks (k-NNs), Logistic Regression (LR), Gaussian Naive Bayes (GNB), and Gradient Boosting (GB).The results indicated that the GB classifier effectively and reliably predicted sleep-related disorders with a notable degree of precision. Furthermore, we acquired substantial comprehension of the variables that influence sleep disorders by analysing class distribution, and correlations, visualising categorical data, and conducting bivariate analysis. In essence, it highlights the effectiveness of ML approaches in precisely identifying sleep problems through the analysis of many lifestyle and health attributes. Other implemented approaches also provide some useful insights into the elements that contribute to sleep difficulties.