Logistic Regression and Decision Tree Predictive Modeling on Sleep Health and Lifestyle Dataset with Analytic Platform

This analysis explores the connections between sleep health and lifestyle factors using the Sleep Health and Lifestyle Dataset. Sleep quality and duration are essential for maintaining overall health and productivity, while factors such as physical activity, stress levels, and cardiovascular health play a significant role in influencing sleep patterns. The research focuses on analyzing trends in sleep duration, quality, and the occurrence of sleep disorders, while also developing predictive models using machine learning techniques. The dataset includes critical metrics such as sleep duration, stress levels, daily steps and cardiovascular indicators like heart rate. Descriptive analysis revealed notable patterns: higher stress levels and low physical activity were strongly associated with poor sleep quality, while daily steps also demonstrated measurable impacts on sleep metrics. Machine learning models, particularly Decision Tree and Logistic Regression, were applied to predict sleep disorders such as Insomnia and Sleep Apnea. Logistic Regression effectively capturing the relationships between lifestyle habits and sleep outcomes has exhibited higher predictive accuracy of 94.69%, which indicates that it correctly predicted the outcomes for approximately 94.7% of the data points. The Decision Tree model has an accuracy of 93.81%, which means it correctly predicted the outcomes for about 93.8% of the data points. The analysis provides valuable insights into how lifestyle choices affect sleep health, highlighting actionable areas for individuals and healthcare professionals to improve sleep quality and overall well-being.