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.
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.
| 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.
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.
The analysis will be divided into 3 segments
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
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.
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
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:
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
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:
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:
Highlight Membership Benefits: Emphasize the additional benefits and conveniences of membership, such as priority access to preferred bike types and potential cost savings.
Promote Bike Variety: Showcase the availability of classic and electric bikes as part of the membership package, emphasizing their popularity among members and the enhanced riding experience they offer.
Membership Incentives: Offer exclusive incentives or discounts to casual users who sign up for membership, highlighting the value proposition and potential savings of membership.
Educational Campaigns: Launch campaigns targeting casual users, highlighting the long-term benefits of membership and how it aligns with their lifestyle.
Trial Programs: Introduce trial membership programs that allow casual users to experience the benefits of membership firsthand, with incentives for continued membership.
Community Engagement: Foster a sense of community among casual users through group rides and events, showcasing success stories from existing members.
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.