Dark Mode
Fitness Tracker User Habit Analysis
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Analysis of consumer usage patterns derived from smart device activity data, initially focused on supporting Bellabeat, a small but growing manufacturer of high-tech products oriented towards women’s health. The resulting statistical output is designed to unlock new business opportunities by revealing how consumers utilise their smart devices. The data categorises users based on their average monthly activity level (High or Low) and presents averaged daily steps, calories, and detailed hourly step counts for these segments. This product demonstrates the benefit of tailoring application notifications based on detected activity habits after a month of monitoring.
Columns
- Id: The unique identifier for the device user.
- ActivityDate: The specific date of the recorded daily activity, standardised to DD/MM/YYYY format.
- TotalSteps: The total number of steps recorded for a user on a given day.
- Calories: The total calories burned recorded for a user on a given day.
- ActivityLevel: A classification applied to the user based on their monthly average steps: 'High' (4,000 steps or more) or 'Low' (fewer than 4,000 steps).
- AvgMonthSteps: The monthly mean of total steps for each user ID.
- AvgMonthCal: The monthly mean of calories for each user ID.
- SumDate: The count of distinct dates with activity records for each user ID.
- Level: Used in aggregated tables to denote the row summation ('High', 'Low', or 'Total').
- Hour_01 to Hour_24: Average step totals for users across the 24 hours of the day, segmented by their ActivityLevel.
- AvgHighSteps/AvgLowSteps: Mean daily steps specifically for the 'High' and 'Low' activity groups, respectively, for a given date.
- AvgHighCalories/AvgLowCalories: Mean daily calories specifically for the 'High' and 'Low' activity groups, respectively, for a given date.
Distribution
The underlying records were processed from merged daily and hourly activity data logs. The dataset focuses on the usage patterns of 33 unique user IDs. Data processing involved substantial SQL transformation, including date standardisation and aggregation of hourly steps into 24 distinct time columns. Analysis shows a strong prevalence of highly active users, with 82% classified in the 'High' activity category and 18% in the 'Low' category. The product includes statistical calculations of averages grouped by these two activity classifications.
Usage
- To inform the development of personalised application reminders or alerts, allowing tailoring based on whether a user is categorised as 'High' or 'Low' activity.
- Identifying specific hours of the day when 'High' activity users are most or least engaged compared to 'Low' activity users.
- Supporting business analysis for health technology companies, such as Bellabeat, by quantifying general smart device usage trends.
- Designing features within fitness tracking applications that encourage specific behaviours based on user segmentation.
Coverage
The data is derived from daily and hourly activity records spanning multiple days. It provides insights into activity and caloric expenditure metrics. The analysis is built upon a sample size of 33 unique individuals. Demographic or precise geographic information is not included, though the analysis is framed within the context of women’s health technology.
License
CC0: Public Domain
Who Can Use It
- Marketing Teams: To create targeted campaigns for smart device users based on their activity habits.
- Product Managers: To refine the notification and user engagement strategies for wearable devices and associated mobile applications.
- Researchers: To study real-world physical activity patterns tracked by fitness technology.
Dataset Name Suggestions
- Wearable Activity Segmentation (33 Users)
- Hourly Step Averages by Activity Group
- Fitness Tracker User Habit Analysis
- Bellabeat Usage Insights
Attributes
Original Data Source: Fitness Tracker User Habit Analysis
QUALITYLoading...