Mission Statement:

Our mission is to uncover the distinctive usage patterns of Cyclistic bikes between annual members and casual riders. By delving into data analytics, we aim to reveal insightful trends that will drive marketing strategies aimed at converting casual riders into loyal annual members. Our goal is to provide actionable recommendations that will empower Cyclistic to optimize its marketing initiatives, enhance customer engagement, and ultimately accelerate business growth and profitability.

Data Source Description:

For this analysis, we will utilize historical trip data provided by Motivate International Inc., under an appropriate license for this case study.The dataset is stored in CSV format and is accessible for download from here. The dataset used for this analysis consists of trip records from Cyclistic bike-share program spanning the past 12 months (from February 2023 until February 2024).

The dataset is organized into rows and columns, with each row representing a single trip record and each column representing a specific attribute of the trip. An example of the table showing 5 trips can be seen below.

Head of table containing the Cyclistic bike data
ride_id rideable_type started_at ended_at start_station_name start_station_id end_station_name end_station_id start_lat start_lng end_lat end_lng member_casual
CBCD0D7777F0E45F classic_bike 2023-02-14 11:59:42 2023-02-14 12:13:38 Southport Ave & Clybourn Ave TA1309000030 Clark St & Schiller St TA1309000024 41.92077 -87.66371 41.90799 -87.63150 casual
F3EC5FCE5FF39DE9 electric_bike 2023-02-15 13:53:48 2023-02-15 13:59:08 Clarendon Ave & Gordon Ter 13379 Sheridan Rd & Lawrence Ave TA1309000041 41.95788 -87.64958 41.96952 -87.65469 casual
E54C1F27FA9354FF classic_bike 2023-02-19 11:10:57 2023-02-19 11:35:01 Southport Ave & Clybourn Ave TA1309000030 Aberdeen St & Monroe St 13156 41.92077 -87.66371 41.88042 -87.65552 member
3D561E04F739CC45 electric_bike 2023-02-26 16:12:05 2023-02-26 16:39:55 Southport Ave & Clybourn Ave TA1309000030 Franklin St & Adams St (Temp) TA1309000008 41.92087 -87.66373 41.87943 -87.63550 member
0CB4B4D53B2DBE05 electric_bike 2023-02-20 11:55:23 2023-02-20 12:05:48 Prairie Ave & Garfield Blvd TA1307000160 Cottage Grove Ave & 63rd St KA1503000054 41.79483 -87.61879 41.78053 -87.60597 member

To ensure data integrity and reliability, we have reviewed the data documentation provided by Motivate International Inc. and conducted initial exploratory data analysis to identify any anomalies or inconsistencies (i.e. checking for negative travel time). We have also ensured compliance with privacy regulations by excluding personally identifiable information of users from our analysis. Overall, the dataset appears to be well-structured and suitable for our analysis, providing valuable insights into the usage patterns of Cyclistic bikes by different user groups.

Data Processing:

To prepare the data for analysis, we aggregated the trip data for the last 12 months into a single comprehensive dataset by joining individual files into a unified big data frame. This consolidation facilitated a holistic view of Cyclistic’s bike usage patterns over the specified period. As part of the data cleaning process, we identified and removed rides with negative time differences between their end and start times. Such occurrences are likely indicative of data entry errors or anomalies and could skew our analysis. By eliminating these discrepancies, we ensured the integrity and accuracy of our dataset, laying a solid foundation for subsequent analysis to derive meaningful insights into Cyclistic’s user behavior and preferences.

Analysis:

The analysis will be divided into 3 segments

1) Ride count vs Week day:

For the first plot (Fig. 1), a bar plot was generated to visualize the total number of rides per weekday, distinguishing between members and casual riders. Each weekday is represented by a bar, with different colors indicating the rider types. The heights of the bars represent the total number of rides for each weekday, while the percentages of member and casual rider rides are displayed within the respective bars. This visualization allows for a clear comparison of ride frequencies between weekdays and highlights any variations in usage patterns between members and casual riders throughout the week.

Fig. 1

Fig. 1

Here is a few comments regarding this figure:

  • Weekday Usage Patterns: The analysis reveals a consistent trend throughout the weekdays, with approximately 70% of rides being attributed to members and 30% to casual riders. This suggests that Cyclistic’s bike usage is predominantly driven by annual members during weekdays, indicating a strong presence of commuters or regular users who rely on the service for daily transportation needs.

  • Weekend Usage Patterns: In contrast, weekends exhibit a more balanced distribution of rides, with member and casual rider contributions nearly equal at around 50% each. This shift in usage patterns on weekends suggests a shift in user behavior, with casual riders making up a larger proportion of total rides during leisure-oriented days.

  • Implications for Marketing Strategy: These findings have important implications for Cyclistic’s marketing strategy. Given the higher concentration of member rides on weekdays, marketing efforts aimed at converting casual riders into annual members could be intensified during this period. Additionally, recognizing the equal contribution of casual riders on weekends, targeted promotions or incentives could be implemented to attract more casual riders and encourage them to utilize Cyclistic’s services during leisure periods.

  • Enhancing Weekend Engagement: To capitalize on the balanced distribution of rides on weekends, Cyclistic could focus on enhancing weekend engagement by offering special promotions, events, or partnerships tailored to appeal to casual riders. This could help increase overall usage and revenue generation during these periods.

2) Average time per ride vs weekday:

For the second plot (Fig. 2), we’ll create a visualization of the average ride time per weekday, segmented by member and casual rider types. This will provide insights into the average duration of rides for each user group across different days of the week.

Fig. 2

Fig. 2

Here is a few comments regarding this figure:

  • User Behavior Understanding: The considerable difference in average ride times suggests distinct usage patterns between member and casual riders. Members tend to take shorter trips, likely for commuting or short-distance travel, as evidenced by the shorter average ride times of around 700 seconds (approximately 11-12 minutes). On the other hand, casual riders exhibit longer average ride times, averaging around 1700 seconds (approximately 28-29 minutes), indicating leisurely or recreational rides.

  • Targeted Marketing Opportunities: Understanding these usage patterns allows Cyclistic to tailor marketing efforts to better cater to the specific needs and preferences of each user segment. For instance:

    • Member-Focused Promotions: Cyclistic can focus on promoting the convenience and efficiency of short rides to attract more members. Highlighting features such as easy access to bikes, quick commutes, and cost-effectiveness for short trips can incentivize more individuals to sign up for annual memberships. Casual Rider Engagement: For casual riders, Cyclistic can emphasize the enjoyment and leisure aspects of biking. Promotions could include leisurely biking routes, weekend getaway ideas, or themed ride events to attract more casual users and encourage longer rides.
    • Revenue Generation Opportunities: By encouraging more short rides among members, Cyclistic can increase ride frequency and overall usage, leading to higher revenue generation through membership subscriptions. Additionally, promoting longer rides among casual riders can boost revenue from pay-per-ride transactions, as longer rides typically result in higher fees.
    • Highlight Cost Savings: Emphasize the cost-effectiveness of annual memberships for casual riders who frequently use the service for longer rides. By showcasing how annual membership offers substantial savings compared to pay-per-ride fees, Cyclistic can incentivize casual riders to transition to membership status.
  • Service Optimization: Insights from the average ride times can also guide operational decisions, such as bike placement, maintenance scheduling, and resource allocation. For example, Cyclistic can strategically position bikes in high-traffic areas for short rides during peak commuting hours and adjust bike availability in recreational areas to accommodate longer rides during weekends or holidays.

3) Type of bike vs membership usage:

In the third bar plot (Fig. 3) we see the type of bike usage count according to membership. This visualization will allow us to see the distribution of bike types used by members and casual riders separately.

Fig. 3

Fig. 3

Here is a few comments regarding this figure:

  • Bike Type Usage: The data show that classic bikes are the most commonly used bike type overall, followed by electric bikes. Docked bikes have the lowest usage compared to classic and electric bikes.

  • Usage by Rider Type: When considering rider type, both classic and electric bikes are used more frequently by members than by casual riders. However, casual riders still contribute significantly to the usage of electric bikes, while classic bikes are predominantly used by members.

  • Marketing and Operational Insights:

    • Bike Availability: Cyclistic can ensure optimal availability of classic and electric bikes, particularly in areas frequented by members, to meet demand effectively. Promotions and Incentives: Tailored promotions or incentives can be offered to encourage more casual riders to use classic and electric bikes, potentially increasing revenue from pay-per-ride transactions.
    • Bike Fleet Management: Understanding the popularity of different bike types among members and casual riders can guide decisions related to bike fleet management, maintenance schedules, and expansion plans.
    • Targeted Marketing: Cyclistic can tailor marketing campaigns to highlight the benefits of using classic and electric bikes for both casual riders and members, emphasizing factors such as comfort, convenience, and eco-friendliness.
    • Highlight Membership Benefits: Emphasize the additional benefits and conveniences that membership offers, such as priority access to preferred bike types (e.g., classic and electric bikes), flexibility in bike usage, and potential cost savings compared to pay-per-ride fees for casual users who frequently utilize Cyclistic services.
    • Promote Bike Variety: Showcase the availability of classic and electric bikes as part of the membership package, highlighting their popularity among members and the enhanced riding experience they offer compared to docked bikes. Emphasize the convenience of accessing different bike types based on user preferences and needs.

Conclusion:

In conclusion, our analysis of Cyclistic’s bike usage patterns has provided valuable insights into the behavior of both members and casual riders. We found that classic and electric bikes are the most popular among members, while docked bikes have lower overall usage. Additionally, while members predominantly use classic and electric bikes, casual riders contribute significantly to the usage of electric bikes. Leveraging these insights, we can implement targeted strategies to encourage more casual users to become members.

Our suggested solutions include:

By implementing these solutions, Cyclistic can effectively incentivize more casual users to become members, expanding its member base, increasing revenue, and fostering long-term customer loyalty and engagement.