Dark Mode
Sleep Quality Prediction Dataset
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset is a fully synthetic collection of sleep and health metrics, designed to offer a detailed overview of how various factors might influence sleep quality and overall health. It is created to simulate a wide range of scenarios and conditions, providing a robust foundation for predictive modelling and analytical studies. Utilising synthetic data ensures a clear representation of potential variations and interactions in sleep and health metrics, making it particularly useful for developing and testing predictive models aimed at uncovering patterns and relationships to guide strategies for improving sleep health. The primary goal is to predict the Sleep Quality Score based on the other synthetic health and sleep metrics.
Columns
The dataset comprises 9 numerical columns, each representing a synthetic measurement:
- Heart_Rate_Variability: Simulated variability in time intervals between heartbeats, ranging from approximately 5.17 to 147.
- Body_Temperature: Artificially generated body temperature in degrees Celsius, with values typically between 35 and 38.1.
- Movement_During_Sleep: Synthetic data on the amount of movement while sleeping, generally ranging from -1.02 to 5.93.
- Sleep_Duration_Hours: Total hours of sleep generated through simulation, with values from approximately 3.11 to 12.4.
- Sleep_Quality_Score: A synthetic score representing the quality of sleep, ranging from 1 to 10.
- Caffeine_Intake_mg: Amount of simulated caffeine consumption in milligrams, spanning from 0 to 400.
- Stress_Level: An index of simulated stress levels, with values from 0 to 10.
- Bedtime_Consistency: Simulated consistency of bedtime routine, on a 0-1 scale, where lower values indicate more inconsistency. Ranges from 0 to 1.
- Light_Exposure_hours: Synthetic hours of light exposure during the day, reflecting typical daylight exposure hours, with values from approximately 0.33 to 14.8.
Distribution
The dataset is provided in a CSV format, specifically named
wearable_tech_sleep_quality_1.csv, with a file size of 152.85 kB. It contains 1000 records (rows) across its 9 columns. As a fully synthetic collection, the data is generated to simulate scenarios rather than representing real-world observations.Usage
This dataset is ideal for:
- Predictive Modelling: Developing and testing models to predict Sleep Quality Score based on various health and sleep metrics.
- Analytical Studies: Uncovering patterns and relationships within simulated health and sleep data.
- Strategy Development: Guiding the creation of strategies for improving sleep health by identifying influential factors.
- Research: Exploring how different factors interact to influence sleep quality in a controlled environment.
Coverage
As a fully synthetic dataset, it does not have a real-world geographic, time range, or demographic scope. It is designed to simulate a wide range of scenarios and conditions to offer a robust foundation for analytical studies, ensuring representation of potential variations and interactions in sleep and health metrics across a hypothetical population.
License
Attribution 4.0 International (CC BY 4.0)
Who Can Use It
- Data Scientists and Analysts: For building and evaluating machine learning models focused on health and sleep.
- Researchers in Health and Sleep Science: To explore hypothetical relationships and test theories without relying on sensitive real-world data.
- Developers of Health Applications: For prototyping and testing features related to sleep tracking and improvement.
- Educators and Students: As a practical resource for learning about data analysis, predictive modelling, and health informatics.
Dataset Name Suggestions
- Synthetic Sleep and Health Metrics
- Sleep Quality Prediction Dataset
- Health Factor Sleep Data
- Simulated Sleep Patterns
- Wearable Tech Sleep Study Data
Attributes
Original Data Source: Sleep Quality Prediction Dataset
QUALITY