Bellabeat Data Analysis Case Study
- majiriok
- Mar 7
- 5 min read
Bellabeat is a high-tech manufacturer of health-focused products for women. By collecting data on activity, stress, sleep, and health, Bellabeat empowers women with knowledge about their health and habits. The company has significant potential to expand its presence in the smart device market. Since its founding in 2013, Bellabeat has grown rapidly, establishing itself as a tech-driven wellness company for women. Urška Sršen, co-founder and Chief Creative Officer of Bellabeat, believes that analyzing smart device fitness data could unlock new growth opportunities for the company. This case study focuses on analyzing smart device data from one of Bellabeat's products to understand how consumers use their devices. Urška has requested high-level recommendations based on the analysis of Bellabeat's consumer data, as these insights will help shape the company's marketing strategy.
BUSINESS TASK:
What are some trends in smart device usage?
How could these trends apply to Bellabeat users?
How could these trends help influence Bellabeat's marketing strategy?
STAKEHOLDERS:
Urška Sršen: Bellabeat’s co-founder and Chief Creative Officer.
Sando Mur: Mathematician and Bellabeat’s co-founder; key member of the Bellabeat executive team.
Bellabeat marketing analytics team: Data analysts responsible for collecting, analyzing, and reporting data that help guide Bellabeat’s marketing strategy.
PRODUCTS:
Bellabeat app: It collects user activity, sleep, stress, menstrual cycle, and mindfulness habits, helping them better understand their health. It seamlessly connects to Bellabeat's line of smart wellness products.
Time: A wellness watch that tracks activity, sleep, and stress while connecting to the Bellabeat app. The watch provides detailed insights into your daily wellness.
Spring: A smart water bottle that tracks daily water intake using state-of-the-art technology. Spring connects with the Bellabeat app to monitor your hydration levels.
Leaf: A wellness tracker that can be worn as a bracelet, necklace, or clip. The Leaf connects with the Bellabeat app to track activity, sleep, and stress.
Bellabeat membership: A subscription-based program offering users 24/7 access to personalized guidance on nutrition, activity, sleep, health and beauty, and mindfulness—all tailored to their lifestyle and goals.
PREPARE:
The datasets used in this analysis were sourced from Mobius on Kaggle and are covered under the CC0 Public Domain license. The datasets were compiled from responses collected through a distributed survey conducted via Amazon Mechanical Turk.
This dataset contains personal health data from 30 Fitbit users who consented to share their personal tracker data. The data includes minute-by-minute measurements of physical activity, heart rate, and sleep patterns. Users' daily activity, steps, and heart rate data provide insights into their habits. The dataset consists of 18 CSV files.
Dataset Limitations:
Since the data is collected from only thirty Fitbit users, it is not representative of the entire fitness tracker industry and therefore has a sampling bias
The dataset contains data from only 30 users, which is a small sample size that limits the analysis.
The data covers 31 days starting from April 12, 2016, rather than the March 12 to May 12, 2016 period.
The initial files displayed below were downloaded from this link.
PROCESS:
For this analysis, I will be using the following datasets:
Data cleaning was performed in Power BI using the following steps for each dataset
Removing duplicates/errors
Changing data types
Splitting and creating columns
Finally, rows with irrelevant data were deleted.
I created data relationships between the tables. The Entity Relationship Diagram (ERD) is shown below:
ANALYSIS:
Active Days
The bar graphs reveal a notable increase in activity on Saturday, where users take more steps, and spend less time being sedentary. In contrast, Sunday appears to be users' least active day.
Active Minutes
Users' active minutes fall into four categories: very active, fairly active, lightly active, and sedentary. Based on average minutes calculated for each category, users spend 81% of their time in sedentary minutes, 16% in lightly active minutes, and only 3% in active minutes (combining fairly and very active).
Hourly Steps
Users are most active between 7 AM and 8 PM, with peak activity occurring from 5–7 PM. During these hours, activity intensity reaches its highest levels. There is a notable decrease in activity between 3–4 PM.
Total Steps vs. Calories
Analysis of the relationship between calories and total steps shows a clear positive correlation: as users take more steps, they burn more calories—a predictable but important finding.
Average Daily Calories and Steps by Time:
Analysis of average calories burned and total steps throughout the day revealed similar patterns. After 6 AM, average steps increased sharply from 0 to over 400 steps and remained between 400–600 steps until 6 PM, after which activity dropped significantly. The pattern of calories burned mirrored the step count pattern, with users burning more calories between 6 AM and 6 PM—likely corresponding to typical working hours when people are most active.
Sleep by Weekday:
Sleep data was collected from 24 users. The analysis shows that the average sleep duration ranged from 400 to 450 minutes (6.6 to 7.5 hours). Users had the longest sleep duration on Sundays, averaging 452 minutes (7.5 hours), and they also spent the most time in bed on this day.
Weight & BMI:
The table displays average weight and BMI data for 8 users. The BMI categories are: healthy (18.5–24.9), overweight (25–29.9), obese (30–39.9), and severely obese (over 40). Among the users, three were in the healthy range, while five were overweight.
FINDINGS:
Users take an average of 7,638 steps per day.
Users spend an average of 16.5 hours per day being sedentary.
Higher activity levels and intensity directly correlate with increased calorie burn.
Users show peak activity levels on Tuesdays and Saturdays, while their activity drops lowest on Fridays and Sundays.
On average, users sleep about 7 hours per day and spend an additional 39 minutes in bed while awake.
Users are most active between 5–7 PM, with activity levels dropping significantly at 3 PM before increasing again.
RECOMMENDATIONS:
Bellabeat could motivate users to start their weekends with a brisk walk or jog to establish a consistent morning exercise routine. The app can achieve this through targeted push notifications, weekend step challenges that connect users with their social networks, and partnerships with wellness influencers as virtual coaches. These strategies would help users stay energized and motivated throughout their wellness journey, especially on weekends.
Launch an educational healthy lifestyle campaign that encourages users to do short exercises during weekdays and longer workouts on weekends—particularly on Sundays, when data shows the lowest step counts and highest sedentary time.
The Leaf wellness tracker can vibrate after detecting prolonged sedentary periods, prompting users to become more active. Similarly, it can remind users to sleep when it detects extended periods of wakefulness in bed.
For customers focused on weight management, Bellabeat can help track daily calorie intake while providing suggestions for nutritious, low-calorie meals at lunch and dinner.
Comments