This is my first Data Analysis Project. I did it as part of Google Data Analytics course. There are three documents, Prepare and Process Data, Analysis, and Findings and Recommendations.
| Rider Type | No of Rides | Percent |
|---|---|---|
| member | 7,121,972 | 64.25% |
| casual | 3,962,010 | 35.75% |
| Total | 11,083,982 | 100% |
Member riders’ daily average number of trips for were much higher than
casual riders. The casual:member ratio was 1:1.8.
Please note that the number of trips is not the same as the number of users.
Casual riders’ daily average number of trips varied considerably day by
day and season by season.
Both groups rode electrical bikes more than classic bikes. There was not much difference between two groups.
Ride patterns by time of the day were differ. On weekdays, member riders
had sharp spikes during morning and evening rush hours, casual riders
did not. On weekends, both groups had the same pattern and did not have
any spike.
Casual riders rode more on weekends than on weekdays. Member riders rode
more on weekdays than on weekends.
Both rider groups rode less during cold seasons, but number of casual
riders’ trips dropped a lot more than member riders.
Casual riders’ had longer riding duration per trip than member riders.
These were always true when consider other factors.
Casual riders’ hot spots were around tourist attractions on both weekdays and weekends. Member riders’ weekday hotspots were near major transportation hubs, business areas and universities, and weekend hotspot were outside business areas.
The popular routes for both groups confirm the hotspot analysis. Casual
riders’ popular routes were long routes that connect tourist hotspots.
Member riders’ weekdays popular routes were short and within dense
commercial areas. For weekends, member riders’ routes were longer and
outside commercial areas.
From the riding behavior, we can assume that majority of casual riders in this data were visitors. They used Divvy bikes to visit many tourist attractions in Chicago area. There is also a small percentage of casual riders that use Divvy bikes to commute to and from business areas.
We can also assume that member riders in this data were people who live or work in Chicago. The use divvy bikes to commute between major transportation hubs and business areas.
The main business problem we try to solve here is “How to maximizing the number of annual members for future growth?” The goal of this analysis is to help “design marketing strategies aimed at converting casual riders into annual members.”
Before any recommendation, we need to consider that can we convert casual riders into annual members? The answer is yes, but for only certain segment of casual riders. The results of this analysis point to that annual members are the people who live or work in Chicago area, and majority of casual riders are visitors. With this in mind, These are the recommendation.
Divvy Bikes infomation
Chicago Information
This analysis cannot be done with out these r libraries:
Map of Chicago provide by Stadia Maps
Chicago Population from Forest Gregg’s github “Chicago-dots”
I also learn a lot form the following r websites.