The Case of Bellabeat
Farzin
2024-08-18
Introduction
Background
Bellabeat is a technology developer of health and wellness products focussed on Women. Founded in 2014 by Urška Sršen and Sandro Mur, it has in the last decade gained 10 million users and improved the health of women in Europe and The United States. Urška - Co-founder and Chief Product Officer requires analysis to answer questions on the completeness of Bellabeat products in the market over existing competing brands to facilitate new areas of opportunity and growth.
Business Task
The goal of this analysis is to understand user behavior from the data collected by smart devices that are not Bellabeat and provide recommendations that will help the company to grow its customer base while making new innovations and improving product engagement.
Data
Data Source
The dataset used in this analysis is a sample of data collected from non-Bellabeat smart devices, available on Kaggle. It includes information on users’ physical activities, sleep patterns, and other health metrics.
Load and Clean Datasets for Analysis and Visualization
Unlike the common practice of loading datasets separately, I have opted to load and merge all relevant files at the outset, streamlining the process for a more cohesive analysis.
Additional Cleaning Steps
I have taken steps to clean the data after merging, including handling NA values, converting Date-Time parameters, and enhancing the dataset by adding new columns to better illustrate relationships within the data along with their summaries.
## Id ActivityDate TotalSteps.x TotalDistance.x
## Min. :1.504e+09 Min. :2016-03-12 Min. : 0 Min. : 0.000
## 1st Qu.:2.320e+09 1st Qu.:2016-04-08 1st Qu.: 0 1st Qu.: 0.000
## Median :4.445e+09 Median :2016-04-19 Median : 0 Median : 0.000
## Mean :4.782e+09 Mean :2016-04-19 Mean : 2179 Mean : 1.552
## 3rd Qu.:6.962e+09 3rd Qu.:2016-04-30 3rd Qu.: 1985 3rd Qu.: 1.360
## Max. :8.878e+09 Max. :2016-05-12 Max. :28497 Max. :27.530
## TrackerDistance.x LoggedActivitiesDistance.x VeryActiveDistance.x
## Min. : 0.000 Min. :0.00000 Min. : 0.0000
## 1st Qu.: 0.000 1st Qu.:0.00000 1st Qu.: 0.0000
## Median : 0.000 Median :0.00000 Median : 0.0000
## Mean : 1.534 Mean :0.05972 Mean : 0.3931
## 3rd Qu.: 1.240 3rd Qu.:0.00000 3rd Qu.: 0.0000
## Max. :27.530 Max. :6.72706 Max. :21.9200
## ModeratelyActiveDistance.x LightActiveDistance.x SedentaryActiveDistance.x
## Min. :0.0000 Min. : 0.000 Min. :0.0000000
## 1st Qu.:0.0000 1st Qu.: 0.000 1st Qu.:0.0000000
## Median :0.0000 Median : 0.000 Median :0.0000000
## Mean :0.1593 Mean : 0.962 Mean :0.0006337
## 3rd Qu.:0.0000 3rd Qu.: 0.840 3rd Qu.:0.0000000
## Max. :6.4000 Max. :12.510 Max. :0.1000000
## VeryActiveMinutes.x FairlyActiveMinutes.x LightlyActiveMinutes.x
## Min. : 0.000 Min. : 0.00 Min. : 0.00
## 1st Qu.: 0.000 1st Qu.: 0.00 1st Qu.: 0.00
## Median : 0.000 Median : 0.00 Median : 0.00
## Mean : 5.533 Mean : 4.35 Mean : 56.61
## 3rd Qu.: 0.000 3rd Qu.: 0.00 3rd Qu.: 63.00
## Max. :202.000 Max. :660.00 Max. :720.00
## SedentaryMinutes.x Calories.x TotalSteps.y TotalDistance.y
## Min. : 0.0 Min. : 0.0 Min. : 0 Min. : 0.000
## 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 0 1st Qu.: 0.000
## Median : 0.0 Median : 0.0 Median : 4081 Median : 2.780
## Mean : 331.3 Mean : 728.8 Mean : 5229 Mean : 3.758
## 3rd Qu.: 727.0 3rd Qu.:1776.0 3rd Qu.: 9388 3rd Qu.: 6.650
## Max. :1440.0 Max. :4562.0 Max. :36019 Max. :28.030
## TrackerDistance.y LoggedActivitiesDistance.y VeryActiveDistance.y
## Min. : 0.000 Min. :0.00000 Min. : 0.000
## 1st Qu.: 0.000 1st Qu.:0.00000 1st Qu.: 0.000
## Median : 2.780 Median :0.00000 Median : 0.000
## Mean : 3.749 Mean :0.07406 Mean : 1.029
## 3rd Qu.: 6.650 3rd Qu.:0.00000 3rd Qu.: 0.980
## Max. :28.030 Max. :4.94214 Max. :21.920
## ModeratelyActiveDistance.y LightActiveDistance.y SedentaryActiveDistance.y
## Min. :0.0000 Min. : 0.000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.: 0.000 1st Qu.:0.0000
## Median :0.0000 Median : 2.090 Median :0.0000
## Mean :0.3886 Mean : 2.287 Mean :0.0011
## 3rd Qu.:0.4700 3rd Qu.: 4.170 3rd Qu.:0.0000
## Max. :6.4800 Max. :10.710 Max. :0.1100
## VeryActiveMinutes.y FairlyActiveMinutes.y LightlyActiveMinutes.y
## Min. : 0.00 Min. : 0.000 Min. : 0
## 1st Qu.: 0.00 1st Qu.: 0.000 1st Qu.: 0
## Median : 0.00 Median : 0.000 Median :134
## Mean : 14.49 Mean : 9.287 Mean :132
## 3rd Qu.: 16.00 3rd Qu.: 12.000 3rd Qu.:233
## Max. :210.00 Max. :143.000 Max. :518
## SedentaryMinutes.y Calories.y Total_Distance TotalVeryActiveDistance
## Min. : 0.0 Min. : 0 Min. : 0.000 Min. : 0.000
## 1st Qu.: 0.0 1st Qu.: 0 1st Qu.: 2.290 1st Qu.: 0.000
## Median : 738.0 Median :1849 Median : 5.030 Median : 0.120
## Mean : 678.6 Mean :1577 Mean : 5.311 Mean : 1.422
## 3rd Qu.:1148.0 3rd Qu.:2496 3rd Qu.: 7.630 3rd Qu.: 1.870
## Max. :1440.0 Max. :4900 Max. :28.030 Max. :21.920
## TotalSedentaryDistance TotalLightlyActiveMinutes Total_Steps
## Min. :0.000000 Min. : 0.0 Min. : 0
## 1st Qu.:0.000000 1st Qu.:117.0 1st Qu.: 3325
## Median :0.000000 Median :196.0 Median : 7142
## Mean :0.001733 Mean :188.6 Mean : 7408
## 3rd Qu.:0.000000 3rd Qu.:263.0 3rd Qu.:10686
## Max. :0.110000 Max. :720.0 Max. :36019
## TotalLoggedActivityDistance TotalLightActiveDistance TotalFairlyActiveMinutes
## Min. :0.0000 Min. : 0.000 Min. : 0.00
## 1st Qu.:0.0000 1st Qu.: 1.730 1st Qu.: 0.00
## Median :0.0000 Median : 3.280 Median : 6.00
## Mean :0.1338 Mean : 3.249 Mean : 13.64
## 3rd Qu.:0.0000 3rd Qu.: 4.710 3rd Qu.: 19.00
## Max. :9.7396 Max. :12.510 Max. :660.00
## TotalCalories TotalTrackerDistance TotalModeratelyActiveDistance
## Min. : 0 Min. : 0.000 Min. :0.0000
## 1st Qu.:1820 1st Qu.: 2.270 1st Qu.:0.0000
## Median :2138 Median : 5.020 Median :0.2000
## Mean :2306 Mean : 5.283 Mean :0.5479
## 3rd Qu.:2786 3rd Qu.: 7.620 3rd Qu.:0.7900
## Max. :5517 Max. :28.030 Max. :6.4800
## TotalVeryActiveMinutes TotalSedentaryMinutes
## Min. : 0.00 Min. : 0
## 1st Qu.: 0.00 1st Qu.: 737
## Median : 2.00 Median :1065
## Mean : 20.02 Mean :1010
## 3rd Qu.: 30.00 3rd Qu.:1254
## Max. :210.00 Max. :2684Analysis
Exploratory Data Analysis (EDA)
- Total Very Active Distance vs Total Steps
This scatter plot displays the relationship between the total
distance covered during very active periods and the total number of
steps taken. The color gradient from yellow to purple indicates the
intensity of activity, with yellow representing fewer steps and purple
indicating more. This plot helps to visualize how the distance traveled
during active periods correlates with the total number of steps.
- Total Very Active Minutes vs Total Calories
This scatter plot illustrates the correlation between the total minutes spent in very active periods and the total calories burned. The color gradient from green to orange represents the intensity of calorie expenditure, with green indicating lower calorie counts and orange representing higher values. The plot provides insight into how time spent being very active influences overall calorie burn.
- Total Steps vs Total Calories
This scatter plot shows the relationship between the total number of steps taken and the total calories burned. The color gradient from blue to red reflects the calorie burn intensity, with blue representing lower calorie expenditure and red indicating higher calorie counts. This graph highlights how increasing step counts relate to changes in calorie expenditure.
- Total Calories by Activity Date
This line plot tracks the total calories burned over time, with data points marked in lime green. The x-axis represents activity dates, and the y-axis shows the total calories burned, with values formatted for clarity. This visualization illustrates trends in calorie expenditure over time, providing insights into how activity levels change daily.
- Total Steps and Calories Burned by Intensity Group
This code generates a scatter plot visualizing the relationship between TotalSteps_Combined and TotalCalories, with color representing the intensity of the steps. The color gradient ranges from light blue (low intensity) to dark blue (high intensity). The plot is faceted by IntensityGroup, allowing for separate panels for different intensity levels.
## Id ActivityHour Calories.x Calories.y
## Min. :1.504e+09 Length:46008 Min. : 0.00 Min. : 0.00
## 1st Qu.:2.320e+09 Class :character 1st Qu.: 0.00 1st Qu.: 0.00
## Median :4.559e+09 Mode :character Median : 50.00 Median : 0.00
## Mean :4.870e+09 Mean : 49.35 Mean : 46.78
## 3rd Qu.:6.962e+09 3rd Qu.: 79.00 3rd Qu.: 82.00
## Max. :8.878e+09 Max. :933.00 Max. :948.00
## TotalCalories
## Min. : 42.00
## 1st Qu.: 62.00
## Median : 81.00
## Mean : 96.12
## 3rd Qu.: 106.00
## Max. :1338.00## Id ActivityHour TotalIntensity.x AverageIntensity.x
## Min. :1.504e+09 Length:46008 Min. : 0.000 Min. :0.00000
## 1st Qu.:2.320e+09 Class :character 1st Qu.: 0.000 1st Qu.:0.00000
## Median :4.559e+09 Mode :character Median : 0.000 Median :0.00000
## Mean :4.870e+09 Mean : 5.667 Mean :0.09445
## 3rd Qu.:6.962e+09 3rd Qu.: 2.000 3rd Qu.:0.03333
## Max. :8.878e+09 Max. :180.000 Max. :3.00000
## TotalIntensity.y AverageIntensity.y TotalIntensity_Combined
## Min. : 0.000 Min. :0.00000 Min. : 0.00
## 1st Qu.: 0.000 1st Qu.:0.00000 1st Qu.: 0.00
## Median : 0.000 Median :0.00000 Median : 2.00
## Mean : 5.781 Mean :0.09635 Mean : 11.45
## 3rd Qu.: 2.000 3rd Qu.:0.03333 3rd Qu.: 15.00
## Max. :180.000 Max. :3.00000 Max. :330.00## Id ActivityHour StepTotal.x StepTotal.y
## Min. :1.504e+09 Length:46008 Min. : 0.0 Min. : 0.0
## 1st Qu.:2.320e+09 Class :character 1st Qu.: 0.0 1st Qu.: 0.0
## Median :4.559e+09 Mode :character Median : 0.0 Median : 0.0
## Mean :4.870e+09 Mean : 149.8 Mean : 153.8
## 3rd Qu.:6.962e+09 3rd Qu.: 19.0 3rd Qu.: 24.0
## Max. :8.878e+09 Max. :10565.0 Max. :10554.0
## TotalSteps_Combined
## Min. : 0.0
## 1st Qu.: 0.0
## Median : 21.0
## Mean : 303.6
## 3rd Qu.: 323.0
## Max. :10750.0
Insights and Trends
Based on the EDA we can see that these insights are valuable for users aiming to maintain their fitness and especially for those undergoing lifestyle changes.
Summary:
Increased Activity and Calories: Higher activity levels, measured in steps and active minutes, are associated with greater calorie expenditure.
Trend Analysis: Time-based analysis of calorie intake and weight provides insights into users’ long-term fitness and health patterns.
Intensity Impact: Different intensity levels affect the relationship between steps and calorie burn, indicating the importance of varying exercise intensity for effective calorie management.
These insights can inform targeted interventions for improving fitness tracking and user engagement in health management applications.
Recommendations
Enhance Data Collection: Bellabeat can use this information to improve the clarity of data collection through their devices.
Account for Medical Conditions: The company should consider adding features to account for medical conditions such as thyroid disorders, diabetes, or multiple sclerosis.
These conditions can significantly impact health and weight management.
- Address a Market Gap: Few mainstream applications currently address these medical conditions.
This gap can hinder progress toward fitness goals and complicate weight loss efforts.
- incorporating recommendations for hydration during activity and meal suggestions for post-exercise within their app could further support users in achieving their health goals.
Conclusions
This case study demonstrates how Bellabeat can use data analytics to enhance its products and grow its customer base. By understanding user behavior and trends, Bellabeat can make informed decisions that drive business success.
References
- Google Data Analytics Professional Certificate on Coursera
- Dataset available on Kaggle
Explanation of the Structure:
YAML Header: Defines the title, author, date, and output format of the document. I’ve included options for a table of contents, section numbering, and a theme for the HTML output.
Introduction: Provides context, introduces Bellabeat, and defines the business task.
Data: Describes the data source and the steps taken to prepare the data for analysis.
Analysis: Includes code and visualizations to perform EDA and uncover insights.
Recommendations: Based on your findings, suggest actions for Bellabeat.
Conclusion: Summarizes the case study and its implications.
References: Lists any sources of data or information used in the analysis.
Additional Tips:
- Code Chunks: Include the
echo = FALSEparameter in code chunks to hide the code if you only want to show the output. - Figures and Tables: Use appropriate captions and labels for clarity.
- Styling: Customize the document’s appearance by adjusting the theme, fonts, and other styling options in the YAML header.
- Narrative: Ensure the document flows logically, with clear explanations and transitions between sections.