I. Introduction

Welcome to my capstone project for the Google Data Analytics Certificate course. In this scenario, 

I am junior data analyst at Cyclistic and my team aims to enhance annual memberships by studying the divergent bike usage patterns between casual riders and annual members. My proposed marketing strategy hinges on persuasive data insights and professional visualizations, awaiting approval from Cyclistic executives. Throughout this endeavor, I navigated real-world data analyst tasks, showcasing my proficiency, skills, and analytical acumen. As a component of the Google Data Analytics Professional Certificate course, this capstone project was conducted utilizing the R programming language in positCloud.

II. Executive Summary

Cyclistic's data analysis reveals distinct usage patterns between casual and member riders, with weekends being peak times for casual riders and consistent usage throughout the week for members. Seasonal trends show significant ridership increases from winter to spring, peaking in the warmer months for casual riders and members alike. Commuting patterns are evident, particularly among members, with surges around typical commute times. Additionally, casual riders tend to take longer rides compared to members.

III. Background

In 2016, Cyclistic launched a successful bike-share program with 5,824 bicycles across 692 stations in Chicago. Offering various bike options, including reclining, hand tricycles, and cargo bikes, Cyclistic aims for inclusivity. While the majority prefer traditional bikes, around 8% use assistive options. About 30% of users commute daily, and annual members are more profitable than casual riders. Pricing options include single ride passes and full-day passes, in addition to annual memberships. To boost growth, Cyclistic plans to convert casual riders to annual members, leveraging existing awareness and loyalty.

A. Key Stakeholders 

Lily Moreno: The director of marketing. Responsible for the development of campaigns and initiatives to promote the bike-share program. 

Cyclistic marketing analytics team: A team of data analysts who are responsible for collecting, analyzing, and reporting data that helps guide Cyclistic marketing strategy. 

Cyclistic executive team: The executive team will decide whether to approve the recommended marketing program.

IV. Objectives

A. Develop marketing tactics aimed at transitioning occasional cyclists into Cyclistic members.

V. Methodology

In Posit Cloud, I utilized R to analyze Cyclistic bike sharing data efficiently. With R's capabilities, I collected, cleaned, and visualized the data, revealing insights into user behavior and ride patterns. The sequence of actions I took included:

A. Data Collection and Preparation

a.  Imported 12 months worth of Cyclistic data into posit Cloud, ranging from March 2023 to February 2024

b. Installed necessary packages (tidyverse, lubridate, janitor, ggplot2, magritte)

c. Combined multiple CSV files into one dataframe 

B. Data Cleaning:

a. Checked column names and removed irrelevant columns

b. Created additional columns for date, month, day, year, and day of the week

c. Calculated ride length in seconds and converted it to numeric values

d. Removed rows with ride lengths of 0 seconds and missing values

C. Descriptive Analysis:

a. Calculated descriptive statistics for ride length (mean, median, max, min)

b. Compared ride length statistics between member and casual users

c. Analyzed average ride time by day of the week for both user types

D. Data Visualization:

a. Visualized the number of rides by rider type and weekday using bar charts

b. Visualized average ride duration by rider type and weekday using bar charts

c. Visualized rides by month and rider type using grouped bar charts

d. Viisualized both start and end times among rider types

E. Additional Analysis:

a. Analyzed ridership patterns by type, time, weekday, and month

b. Examined trends in ride frequency and duration for different rider types

To view the R script utilized in this analysis, please click here

VI. Data Analysis & Visualizations

RIDE START AND END TIMES

To validate the hypothesis regarding member riders' commuting patterns, four visualizations were created illustrating the start and end times of rides by ridership category. The analysis revealed a significant surge in both ride initiations and completions by members around 8 a.m., aligning with morning commute trends. Conversely, start and end times for casual riders exhibited a gradual rise from morning to evening hours, peaking around 5 p.m. This reinforces the notion that casual riders predominantly use bikes for leisure, while members rely on them for dedicated, regular journeys.

VIII . Recommendations

• Introduce a new tier of annual membership at a reduced price, offering a set number of rides within a specified timeframe (e.g., weekly or monthly), as opposed to the existing annual membership model.

• Launch a sale marking the transition from winter to spring, offering discounts on annual memberships.

• Proactively promote specialized bikes for individuals with disabilities, leveraging targeted marketing efforts and partnerships with advocacy groups to raise awareness.

IX. Conclusion

Cyclistic's data analysis highlights distinct ridership patterns between casual and member riders, with opportunities for targeted strategies to boost annual membership. Additionally, the company's commitment to inclusivity, exemplified by its accessible bike offerings, underscores its dedication to serving diverse communities. Moving forward, leveraging these insights and fostering accessibility awareness can drive further growth and engagement for Cyclistic.

X. Next Steps

•  Implement targeted marketing campaigns to promote annual memberships, leveraging insights from ridership patterns.

• Explore further enhancements to accessibility offerings and actively communicate these features to potential riders.

• Conduct customer surveys or focus groups to gather feedback on current services and preferences.

• Use gathered feedback to inform future initiatives aimed at improving user experience and increasing ridership engagement.

• Continuously monitor ridership trends and market dynamics for adapting strategies and maintaining competitiveness in the bike-share industry.

XI. References

Source: Cyclistic, publicly available data. This data has been made available by Motivate International Inc. under this license.