Bellabeat User Behavior Analysis
Project Overview
This analysis examines the behavior patterns of 35 Bellabeat Leaf users, focusing on their interactions with fitness tracking technology and its impact on daily activities. The dataset, derived from Fitbit users between March and May 2016, provides insights into health metrics and user engagement trends. This project has been instrumental in developing skills in data aggregation and outlier detection.
Navigation
Access the following sections via the dropdown menu:
- Home: This landing page
- Insight: Key data findings
- Visual: Scatterplot correlation graphs
- Recommend: Data-driven recommendations
- Table: User averages for visualizations
Analysis Objectives
- Identify trends in smart device usage
- Apply findings to Bellabeat customer base
- Inform Bellabeat marketing strategy
Deliverables
- Concise summary of the business task
- Description of data sources
- Data cleaning and manipulation documentation
- Analysis summary
- Key findings with supporting visualizations
- High-level recommendations based on analysis
Data Overview
- Source: Fitabase Data (health and activity metrics)
- Metrics include:
- Physical activity levels
- Calorie expenditure
- Heart rate measurements
- Step counts
- Sleep patterns
- Exercise intensity
- Data processing:
- Aggregation using DuckDB with Python
- Consolidated tables creation
- Outlier and missing value assessment
- Dataset: Available on Kaggle
Data Limitations
- Sample Size: Limited to 35 unique users
- Tracking Consistency: Irregular user tracking patterns
- Outliers: Presence of significant outliers
- Data Gaps: Missing days and metrics (e.g., height)
- Time Frame: Two-month period (March–May 2016)