This project analyzes sleep health data to identify the key behavioral and physiological factors influencing sleep quality, duration, and the occurrence of sleep disorders.
The objective is to move beyond general wellness assumptions and provide a data-driven understanding of what actually impacts sleep outcomes.
Sleep health is a critical component of overall well-being, affecting productivity, cognitive performance, and long-term medical conditions.
Modern healthcare and wellness platforms commonly focus on:
- Physical activity tracking (steps, exercise levels)
- General lifestyle recommendations
However, despite increased engagement with these interventions, sleep-related issues remain prevalent.
This highlights a key challenge:
Current approaches may not be targeting the most impactful drivers of sleep health.
Healthcare and wellness systems often lack clarity on:
- Which factors most significantly affect sleep quality and duration
- Whether physical activity alone improves sleep outcomes
- How physiological conditions contribute to sleep disorders
As a result:
- Recommendations remain generic
- High-risk individuals are not effectively identified
- Interventions fail to deliver meaningful improvements
A structured analysis was conducted using SQL-based aggregation and segmentation across multiple dimensions:
-
Behavioral Factors
- Stress levels
- Physical activity
-
Physiological Factors
- BMI categories
- Health-related attributes
-
Sleep Metrics
- Sleep duration
- Sleep quality
- Sleep disorder classification
The analysis focuses on identifying relationships between these variables and overall sleep outcomes.
Higher stress levels are strongly associated with:
- Reduced sleep duration
- Lower sleep quality
This indicates that stress is the most influential behavioral factor affecting sleep outcomes.
Increased physical activity shows a positive relationship with sleep quality.
However:
- It does not significantly reduce the occurrence of sleep disorders
This suggests that activity alone is not a comprehensive solution.
Higher BMI categories are associated with a greater prevalence of sleep disorders.
This highlights the importance of physiological health in determining sleep risk.
A significant portion of the population experiences sleep-related conditions such as insomnia and sleep apnea.
This reinforces the need for targeted and data-driven interventions.
Metrics such as daily steps do not strongly differentiate between individuals with and without sleep disorders.
This indicates that:
Not all activity translates into meaningful health outcomes.
The findings highlight key gaps in current approaches to sleep health:
- Activity-focused strategies are incomplete
- Stress management is underemphasized
- High-risk individuals are not adequately targeted
A shift toward integrated behavioral and physiological analysis is required.
Based on the analysis:
- Prioritize stress management as a core component of sleep improvement strategies
- Move beyond step-based metrics and incorporate stress and recovery indicators
- Identify and target high-risk individuals based on BMI and stress levels
- Develop personalized, data-driven recommendations
- Integrate multiple health signals into a unified monitoring framework
- 🧾 SQL Scripts → Data extraction, aggregation, and analysis
- 📓 Dataset → Sleep health and lifestyle data
- 📄 Report → Detailed findings and methodology
- Load the dataset into a SQL environment
- Execute queries to reproduce analysis
- Review results to explore relationships across variables
This project demonstrates that sleep health is influenced more strongly by stress and physiological conditions than by general activity levels.
Improving outcomes requires moving beyond generic activity tracking toward targeted, data-driven health interventions.
This project reflects an analytical approach focused on:
- Identifying meaningful health risk factors
- Challenging common assumptions in wellness analytics
- Translating data into actionable healthcare insights