Introduction

As part of my Google Data Analytics course, I dove into the world of fitness trackers, specifically analyzing data from Bellabeat devices. Utilizing a public dataset from Kaggle, I embarked on a mission to delve into user behavior patterns and glean valuable insights to help Bellabeat optimize their offerings and enhance the user experience.

Data Cleaning and Manipulation

To facilitate analysis and import into RStudio, I downloaded the dataset from Kaggle and renamed the files for clarity. Subsequently, I loaded the Tidyverse package and imported the datasets. Examining the tables, I identified significant redundancy across several of them. To streamline the analysis and focus on key insights, I removed these redundant tables, resulting in the following Two:

Before

After

Missing Information and Inconsistent Data Hinder Analysis

While the Kaggle page offered valuable data from Bellabeat, some crucial information was missing, hindering thorough analysis. Notably, the distance units were absent for all tables, making it impossible to determine the actual travel distances of participants. Given Bellabeat’s global reach, assuming the metric system is used becomes risky. Guessing units compromises data integrity and introduces uncertainty.

Furthermore, inconsistencies between tables regarding participant information raise concerns. This inconsistency makes it difficult to draw meaningful conclusions across datasets.For future analysis, a more comprehensive and standardized dataset would be preferable, ensuring consistent units and participant information for reliable interpretation.

Visualizations

After combining the tables, I exported them to CSV and imported them into Tableau. I used the dates on the x-axis and created separate line and bar graphs for the topics I decided were most important for this analysis.

Error Error Error

User Activity Analysis: Fluctuations and Potential Explanations

Reviewing user activity data reveals significant dips throughout the months, particularly among lightly active users. While menstrual cycles, considering the target audience, could be a factor, the small sample size limits generalizability and might be heavily influenced by individual habits. To gain more conclusive insights, increasing the sample size and segmenting data by demographics, activity levels, and potentially menstrual cycles (ethically) is recommended. Additionally, exploring external factors and defining “lightly active” criteria would provide a clearer picture. By addressing these limitations and conducting further investigation, we can gain a deeper understanding of user behavior and develop effective strategies to improve engagement and activity levels.

Calories Burned vs Distance Traveled

While it’s tempting to think that simply increasing the distance you travel guarantees a significant calorie burn, it’s important to remember that burning calories is a multi-faceted process. Factors like intensity, weight, terrain, and even the duration of your workout all play a role in determining the total calorie expenditure. While a quick jog around the neighborhood can definitely be an effective way to burn calories, the exact amount will vary depending on your individual characteristics and the specifics of your jog. So, while distance shouldn’t be completely discounted, it’s crucial to consider the bigger picture when aiming for optimal calorie burning.