Customer Insights Analysis for a Bike Company — Part 1
Analysing over 5 million ride records to extract actionable insights on customer behaviour, drive member conversion, and provide data-backed recommendations for revenue and operational growth.
Overview
A bike rental company with over 5 million annual ride records needed a clearer picture of who their customers were, how they used the service, and where untapped revenue growth was hiding. Converting casual riders to paid members was identified as the highest-value business opportunity.
This project delivers a comprehensive analysis of customer behaviour, segmentation, and product usage patterns — with targeted recommendations for marketing, member conversion, and operational efficiency.
Key Findings
- The Conversion Gap: Casual riders accounted for a significant share of total rides but generated lower per-ride revenue than members. Closing even a fraction of the conversion gap represented a substantial revenue opportunity.
- Usage Pattern Divergence: Members used the service for consistent weekday commutes, while casual riders concentrated usage on weekends and summer months — suggesting different messaging strategies are needed for each segment.
- High-Value Stations: A subset of stations generated disproportionate casual rider traffic, identifying prime locations for targeted membership conversion campaigns and promotions.
- Bike Type Preference: Classic bikes dominated member usage, while casual riders showed a higher preference for electric bikes — pointing to pricing and product bundling opportunities in the member tier.
Methodology
Data Processing
5M+ ride records were cleaned and processed in Python using Pandas. Missing station data, outlier durations, and erroneous coordinates were handled before analysis.
Customer Segmentation
KMeans clustering was applied to segment riders by usage frequency, ride duration, time of use, and bike type preference — creating distinct customer profiles for targeted strategy development.
Tableau Visualisation
Findings were built into an interactive Tableau dashboard covering customer segment profiles, station performance, seasonal trends, and product mix — supporting the business recommendations.
Explore the Project
Read the full analysis report or browse the code and data on GitHub.