Embedded Files
This case study is completed for Google's Data Analytics program. The aim of this study is to uncover new growth opportunities for Bellabeat by analyzing smart health tracker data. Bellabeat is a wearable-tech company that specializes in health focused products for women. The insights gained from the analysis will help guide the company's marketing strategy and future growth opportunities.
To analyze how consumers use other smart devices on the market, I will analyze third party data for smart device usage. Fitbit Fitness Tracker Data, which is publicly available through Kaggle, explores the daily habits of smart device users, including minute-level output for activity, heart rate, and sleep monitoring. The data set used contains fitness tracker activity from thirty Fitbit users.
The findings from this analysis will then be applied to the company's Leaf bracelet.
Guiding questions
Guiding questions
What are some trends in health tracker usage?
How can Bellabeat use these insights to understand customers better?
What growth opportunities can be identified from the data analysis?
The Process
R packages are installed or retrieved from the library to the workspace.
The data is first downloaded and stored locally in csv format, which is then imported into RStudio for storage and analysis.
Next, data is scrubbed and organized, to make it easier to analyze. The "head" function is used to return a fewer number of rows to preview.
This summary table does a deeper dive into the fitness data of users from the Fitbit data sets to make the numbers and quartile information more visually clear.
Exhibits
This visualization shows a positive correlation between total time in bed and time spent asleep. The graph is upward sloping, which suggests that the more time you spend in bed, the more time you will be asleep.
*time shown in minutes
Here, I used ggplot to illustrate the data with a scatter plot and a trend line to observe the relationship between total steps and calories burned. As we can see, the more steps the user takes, the more calories he or she burns.
Most of the users in this data set are sedentary (59%), followed by lightly active (36%)
This box & whisker plot shows the quartile information and distribution of calories burned by each user type. Very active participants generally burned more calories compared to other types.
Insights from the case study
The Fitbit health tracker data set shows most users tend to be sedentary and burn less calories overall compared to users who are more active*. We also learn that a higher step count correlates to more calories burned.
Since 59% and 36% of users are categorized as "sedentary" and "lightly active" in this study, Bellabeat can use the findings to target these user types to promote more physical activity.
A more streamlined and personalized smartphone integration with the Bellabeat Leaf bracelet is a way to encourage healthy behavior.
The company can also consider creating and fostering a community of active Bellabeat Leaf users with its app, where they can set goals and see daily activity and trends.
*according to active minutes
Page updated
Google Sites
Report abuse