This repository contains capstone project of Google Data Analytics course - Case Study 1: Cyclistic Bike-Sharing.
Cyclistic is a bike-sharing company located in Chicago and has been operating since 2016. The company has a large cycling network with total 692 stations across the city and 5,824 bicycles equipped with lock and geotracking tool. There are 2 types of memberships available for users: casual rider and annual member.
The analyst team wants to understand how casual riders and annual members use Cyclistic bikes differently. From the insight, the team will design a new marketing strategy to convert casual riders into annual members.
For this project, I use 1-year Cyclistic riding data from November 2021 to October 2022. Datasets are available in this link.
I use 3 tools to complete this project:
- R to load, clean, transform, and analyze data.
- Microsoft Excel to save outputs from R and create tables.
- Microsoft Power BI to create visualization and report.
Actually, we should use Tableau for this project because that is the visualization tool taught in this course. But based on my experience, I prefer using Power BI. Also, for visualization and report, there is no much difference between Tableau and Power BI.
Because the size of each dataset is quite large - more than 100 MB for each monthly dataset, so I analyzed each dataset separately in each R-file. At the end, there are 12 R-files contain analysis for each month. But, I only upload 1 R-file here because the code in files are same except for dataset file name.
I use 2 libraries for this analysis:
tidyversefor general analysislubridatefor date/time analysis.
- In general, number of member-users was larger than casual-users, except in summer months. As shown in the table and chart above, in July 2022, number of casual-users was only slightly lower than number of member-users.
- Number of casual-users reached its peak during summer months: June, July (maximum) and August.
- There were 2 types of bike for member-users: classic and electric; while casual users had 3 options: classic, electric, and docked.
- Average ride-time for casual-users was longer than member-users. Casual-users rode their bike for 23 to 33 minutes, while member-users only for 11 to 13 minutes.
- For casual-users, their favorite start and end station was Streeter Dr and Grand Ave; while for member-users, it varied based on months.
- Both casual-users and member-users has similar favorite for start and end hour i.e. at 17 p.m. Since their average ride-time was less than 1 hour, so most of the users rode their bike starting at 17.00 p.m and finished before 18.00 p.m.
- Based on analysis above, we can see that casual-users reached maximum number at summer time, from June, July and August; they started and ended their rides at Streeter Dr and Grand Ave Station; between 17.00 p.m to 18.00 p.m.
- Therefore Cyclistic Company should make event to promote the benefit of membership to these casual-users on either June, July (best month), or August, in Streeter Dr and Grand Ave Station, at 17.00 p.m. to 18.00 p.m.
