Urška Sršen and Sando Mur founded Bellabeat, a high-tech company that manufactures health-focused smart products. Sršen used her background as an artist to develop beautifully designed technology that informs and inspires women around the world.
To analyze smart device usage data in order to gain insight into how
consumers use non-Bellabeat smart devices.
To select one Bellabeat product.
To apply insights in presentation.
UrškaSršen: Bellabeat’s cofounder and Chief Creative
Officer
SandoMur: Mathematician and Bellabeat’s cofounder; key
member of the Bellabeat executive team
Bellabeat marketing analytics team: A team of data
analysts responsible for collecting, analyzing, and reporting data that
helps guide Bellabeat’s marketing strategy
Public data that explores smart device users’ daily habits. FitBit Fitness Tracker
Data (CC0: Public Domain, dataset made available through Mobius
This Kaggle data set contains personal fitness tracker from thirty
Fitbit users. Thirty eligible Fitbit users consented to the submission
of personal tracker data, including minute-level output for physical
activity, heart rate, and sleep monitoring. It includes information
about daily activity, steps, and heart rate that can be used to explore
users’ habits.
The data downloaded and stored on PC in archive.zip folder.
Exported data organized in 2 folders:
Fitabase Data 3.12.16-4.11.16 included 11 csv files
and Fitabase Data 4.12.16-5.12.16 included 18 csv files
The data organized in wide format.
The data is obtained from the FitBit device, which is widely used for monitoring physical activity. However, there may be measurement errors due to sensor inaccuracies or incorrect device usage. It’s also important to consider that the data may be incomplete due to missed days or lack of synchronization.
The data is unique in the sense that it is collected individually for each user. It is primary data that has not undergone significant processing or transformation prior to publication. It is the primary data.
The data includes various aspects of physical activity, such as step count, heart rate, activity level, sleep, etc. However, it may lack important contextual information (e.g., users’ health status or lifestyle), which could limit the depth of analysis.
The data is likely consistent in terms of time and format since it is automatically collected by the device. However, inconsistencies may arise due to missing data or changes in user behavior while wearing the device (e.g., if the user forgets to wear it).
The data is available in its raw form, with minimal processing. This is good for maintaining originality but may require significant preprocessing and cleaning before analysis. It is important to account for possible data gaps and anomalies.
FitBit Fitness Tracker data represents a unique and reliable source of information on users’ physical activity. However, to obtain accurate results, careful data cleaning is necessary, along with consideration of possible measurement errors and contextual limitations.
When working with FitBit Fitness Tracker Data, it is crucial to address several key aspects, including licensing, privacy, security, accessibility, and data integrity.
Addressing Licensing: attributed the source of the data appropriately in documentation.
Addressing Privacy: implemented anonymization techniques, such as removing user IDs or aggregating data, to ensure that individual users cannot be identified from the dataset. Addressing Security: stored the data in secure, encrypted environments with access controls in place. Used secure methods for transferring data and ensured that any sharing of data is done in compliance with security protocols.
Addressing Accessibility: offered the data in multiple formats (e.g., CSV, Excel) and ensured that tools used for analysis are compliant with accessibility standards, such as WCAG (Web Content Accessibility Guidelines).
Verifying Data Integrity: implemented data validation procedures, such as checking for missing values, duplicates, and outliers. Used checksum or hash functions to ensure that data has not been altered during transfer. Cross-validate with other data sources or documentation to confirm accuracy.