Google Analytics Case Study Project.
Welcome to My Data Analytics Portfolio.
I am Mr Matthew Ternenge Beeun, an aspiring data analyst with a passion for transforming raw data into actionable insights. This portfolio showcases my work on the Bellabeat case study, where I applied SQL, R, and Tableau to clean, analyze, and visualize user behavior data from smart wellness devices.
The goal of this project was to uncover patterns that could inform Bellabeat’s business strategy and marketing decisions. Below, you’ll find my datasets, code files, visualizations, and stakeholder report—all organized for clarity and impact.
Table of Contents
1. Project Overview
2. Data Cleaning (SQL)
3. Visualizations. (Tableau)
4. Stakeholder Report (R Markdown)
5. Downloadable Files
6. External Links(Github, Kaggle)
1. Project Overview
Bellabeat Case Study
This portfolio project explores user behavior data from Bellabeat, a wellness tech company that manufactures smart devices for tracking fitness, activity, sleep, and health metrics. The goal is to uncover actionable insights that can inform Bellabeat’s marketing strategy and product development.
Using a combination of SQL, R, and Tableau, I cleaned and analyzed datasets containing daily activity logs, sleep patterns, weight records, and calorie burn. The project follows the full data analytics process—from data cleaning and transformation to visualization and stakeholder reporting.
Business Task & Analytical Questions
Business Task: As a marketing analyst for Bellabeat, the main objective is to analyze the daily fitness and wellness data of current users to understand how they are using the smart devices. The goal is to translate these behavioral patterns into actionable marketing strategies that can boost user engagement, drive product development, and convert more Bellabeat app users into Leaf device customers.
Key Analytical Questions:
1. How are Bellabeat users currently categorized by engagement level (e.g., highly active, moderate, sedentary), and what are the key differences in their usage habits (activity, sleep, time of day)?
2. Is there a correlation between daily activity metrics (steps, distance) and sleep quality/duration? How can Bellabeat use this relationship to encourage holistic wellness?
3. What are the key usage trends over a typical week or day? Which days and times show the lowest activity, and which show the most sleep, to inform optimal product messaging and push notification timing?
4. How can the insights from this general-use data inform the marketing strategy for the female-centric Leaf product specifically?
Tools Used
SQL for data cleaning and insertion
R for reporting
Tableau for interactive dashboards
GitHub Portfolio Hosting
Kaggle for dataset sharing and notebook presentation
To ensure the accuracy and usability of the Bellabeat dataset, I performed extensive data cleaning using SQL. This involved:
Removing duplicates and null values from activity, sleep, and weight logs
Standardizing date formats and column names for consistency
Filtering out invalid entries, such as unrealistic step counts or missing BMI values
Merging datasets by
IdandActivityDateto create a unified view of user behavior
Each cleaning step was documented in my changelog, which are available in the folder below.
This process laid the foundation for reliable analysis and visualization.
A. Link for my cleaning scripts for the first 12 tables:
Link: insert_cleaned_data_12_tables
B. Link for my cleaning scripts for the first 6 tables:
Link: insert_cleaned_data_6_tables
C. link for the Virtual table script used for analysis
Link: vw_user_daily_summary
D. Link for the Changlog, a documentation for cleaning, analysis and reporting processes.
Link: Changelog
3. Visualizations
Using Tableau, I created interactive visuals while I am still working on my dashboard to explore:
Daily activity trends (steps, calories, distance)
Sleep patterns and their correlation with activity
BMI distribution across users
User segmentation based on engagement levels
These visuals helped identify behavioral patterns and informed the final recommendations. You can view the visuals while a post the dashboard soon
## 3.5 Key Findings & Insights
- User Segmentation is Key: By examining the distribution of daily activity, we segmented users into three main groups: Highly Engaged (log activities daily), Moderately Engaged (log activities 3-5 times a week), and Low Engagement/Sedentary (log activities 1-2 times a week or less). The Low Engagement group represents a major churn risk but also the largest opportunity for re-engagement marketing.
- The Weekend Drop-Off: A significant finding was the variation in activity by day. Users showed the highest overall activity and steps during the middle of the week (Tuesday to Thursday). However, total sedentary minutes and average time asleep were highest on the weekend, suggesting a necessary shift in product messaging to encourage consistent daily activity, regardless of the day.
- Sleep vs. Activity: We observed a correlation indicating that users with higher total daily steps also tended to log slightly more minutes of total sleep, though the relationship was not linear. This reinforces Bellabeat's holistic wellness message, showing that promoting activity aligns with promoting rest. However, there are significant outliers—users who are highly active but log poor sleep—indicating a perfect target for product features focused on recovery.
- Time-Based Inactivity: Analysis of the hourly log data showed that the peak time for sedentary activity is between 7 PM and 10 PM. This provides an ideal window for personalized in-app reminders or notifications promoting mindfulness or winding down routines.
4. Stakeholder Report
The final report, written in R Markdown, summarizes key findings and presents actionable insights for Bellabeat’s marketing team. It includes:
Executive summary
Data methodology
Key metrics and trends
Strategic recommendations
The report is designed for non-technical stakeholders and is available in the folder below:
Strategic Recommendations
Based on the key findings, I recommend the following three strategies for the Bellabeat marketing and product development teams:
- Develop a Weekend Re-engagement Campaign: Target Low Engagement and Moderately Engaged users on Friday evenings with a notification like, "Keep your momentum going! Try a relaxing weekend walk," to counteract the observed weekend drop-off in activity.
- Create an "Optimize Recovery" Feature: Target the group of highly active users who log poor sleep. This feature should provide personalized tips or guided meditations during the observed peak sedentary time (7 PM - 10 PM), directly addressing the need for balance between intense activity and adequate recovery.
- Implement Personalized "Wellness Tiers": Use the defined user segments (Highly Engaged, Moderate, Low Engagement) to customize the app experience. For example, send tips on new app features to Highly Engaged users, and send motivational progress reports to Moderately Engaged users to encourage a habit loop.
Downloadable Files Link:
1. Analysis Ready File: bellabeat_user_summary
2. 18 Raw files cleaned for this analysis dowloaded from Kaggle:
Furthermore, this portfolio project con be accessed on github through this link:
Case Study Project link: Portfolio
FOOTNOTE:
This project demonstrates my ability to work through the full data analytics pipeline—from raw data ingestion and cleaning with SQL, to insightful visualizations in Tableau, and stakeholder-ready reporting in R Markdown. By analyzing user behavior from Bellabeat’s smart wellness devices, I uncovered patterns that can inform strategic decisions around marketing, product development, and user engagement.
Through this case study, I’ve showcased not only my technical proficiency in SQL, R, and Tableau, but also my ability to communicate findings clearly and effectively to non-technical audiences. I’m passionate about using data to drive meaningful outcomes, and this portfolio reflects my commitment to analytical rigor and business impact.
I can be contacted through the following:
Kaggle: My Kaggle Profile Link
Github: My Github Profile Link
linkedIn: beeun-matthew
Email: matthewbeeun@gmail.com, bummpt90@gmail.com
Phone: +2348115231834, Business WhatsApp: +2349117561716
Comments
Post a Comment