This data analysis case study is a capstone project for the Google Data Analytics Professional Certificate.
In this case study, I am a data analyst working on the marketing analyst team at Bellabeat, a high-tech manufacturer of health-focused products for women. The CCO of Bellabeat believes that analyzing smart device fitness could help unlock new growth opportunities for the company.
I am tasked with focusing on one of Bellabeat's products and analyzing smart device usage data to gain insight into how consumers are using their smart devices. The insights I discover will help guide marketing strategy for the company. This analysis will be delivered to the Bellabeat executive team along with my high-level recommendations for Bellabeat's marketing strategy.
I began this project by asking relevant questions to help guide my analysis.
- What are some trends in smart device usage?
- How could these trends apply to Bellabeat customers?
- How could these trends help influence Bellabeat's marketing strategy?
After contemplating these questions I arrived at the roadmap below.
- Does Bellabeat's marketing strategy align with how consumers use their smart devices?
- Are consumers using their non-Bellabeat devices differently?
- The business task is to analyze smart device usage data to learn how consumers use their devices.
- The key stakeholders are Bellabeat's CCO, Bellabeat's cofounder, and the marketing strategy leaders.
Based on the business task and the scenario, I have identified the following delvierables:
- Analysis of how consumers use their devices.
- Apply insights to one of Bellabeats products.
- Provide high-level recommendations.
- Presentation of findings for the executive team.
The CCO of Bellabeat encouraged me to use the FitBit Fitness Tracker Data from Kaggle. This dataset contains personal fitness tracking data from 30 fitbit users. All of these users have consented to the submission of this data. This data is CC0: Public Domain, which means that it is not under copyright restrictions. This data can be copied, modified, distributed, and even used for commercial purposes without asking permission.
The product in Bellabeat's lineup that is most similar to FitBit is the "Leaf." The Bellabeat Leaf is a smart device worn on the wrist that tracks activity, sleep, menstrual cycle, and stress sensitivity. Given the similarity in features of these devies, any insights derived from the FitBit dataset will be applied to the Bellabeat Leaf.
A possible limitation of this data is that it was gathered in Q2 2016. In the rapidly advancing consumer electronics industry, a five year gap in data could lead to potentially inaccurate results that are not reflective of the current consumer climate. Furthermore, there is not enough data. The sample size is too small and the date range is too short. If given more time or resources, I would either conduct a new survey to capture more relevant data or request an extension to find a more relevant data source. My concerns about this data will be included in the final presentation to the stakeholders.
Since the FitBit dataset is a collection of multiple CSV files, I have chosen to use SQL (Google BigQuery) and Tableau to conduct the analysis. For the presenation to the executive team, I have chosen to use Google Slides.
While inspecting the data, if any transformations are necessary I will maintain accurate documentation to track them.
After reviewing these datasets, I once again became concerned that there is not enough data to base an entire marketing strategy on. In terms of cleaning steps, the datasets are relatively clean. There are only minor issues that are easily corrected, such as data type inconsistencies. For example, the weight loss dataset and sleep dataset have datetime values instead of date values.
I recommend that Bellabeat might consider investing in studies to gather more data about user preferences. Specifically, conducting surveys about how consumers use their devices. Having private ownership of this data will also be an asset to Bellabeat. Unlike publically available datasets, such as Kaggle, private datasets provide a strategic advantage because they allow Bellabeat to gain insight into data that the competition does not have access to.
However, based on the FitBit dataset that I have been provided, I have come to the following conclusions:
- 47% of users wear their FitBit while they sleep.
- Users only log an average of 320 steps per day. This is approximately 1/6 of a mile per day.
- Users are sedentary 69% of the day.
Based on the above conclusions, it is important that Bellabeat's marketing department emphasize the comfort and style of the Bellabeat Leaf in a new strategic marketing campaign. Almost half of the FitBit users wore their device while sleeping. The users in the dataset also tended to value lifestyle uses, rather than active uses, with users being sedentary almost 70% of the day.
Author: Michael Mishkanian
For all questions and inquiries, please contact me on LinkedIn.