From 5e094c9ebdb0794b1401101ef31ef81c5a76c6ec Mon Sep 17 00:00:00 2001 From: Ken Liu Date: Tue, 7 Jan 2025 17:35:40 +0800 Subject: [PATCH] Rename html file --- ...c-analysis.html => cyclistic-analysis.html | 0 docs/index.html | 2377 +++++++++++++++++ 2 files changed, 2377 insertions(+) rename docs/cyclistic-analysis.html => cyclistic-analysis.html (100%) create mode 100644 docs/index.html diff --git a/docs/cyclistic-analysis.html b/cyclistic-analysis.html similarity index 100% rename from docs/cyclistic-analysis.html rename to cyclistic-analysis.html diff --git a/docs/index.html b/docs/index.html new file mode 100644 index 0000000..d9aaf78 --- /dev/null +++ b/docs/index.html @@ -0,0 +1,2377 @@ + + + + + + + + + + + + + + + +Cyclistic Bike-Share Analysis + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + +
+
+
+
+
+ +
+ + + + + + + +

+
+

Executive Summary

+

This analysis examines Cyclistic bike-share data from December 2023 +to November 2024 to identify strategies for converting casual riders +into annual members. The project revealed distinct usage patterns +between casual riders and annual members, with key differences in ride +timing, duration, and location preferences. Based on these insights, I +developed targeted recommendations for converting casual riders to +annual members.

+

+
+

Key Findings:

+
    +
  • Members primarily use bikes for commuting, with peak usage during +rush hours
    • +
  • Casual riders prefer weekend and leisure rides, with longer average +trip durations
    • +
  • Significant seasonal variation exists, particularly among casual +riders
    • +
  • Station usage patterns differ markedly between members and casual +riders
    • +
+ + + + + + + + + + + + + + + + + + + + + +
+Metric + +Value +
+Total Ride Records + +5,907,256 +
+Unique Ride Records + +5,906,058 +
+Member Percentage + +63.3% +
+

+
+
+
+

1. Introduction

+

+
+

1.1 Project Overview

+

Cyclistic is a bike-share company operating in Chicago with a mission +to maximize the number of annual memberships, which are more profitable +than casual rides. This analysis aims to understand how annual members +and casual riders use Cyclistic bikes differently to inform marketing +strategies for converting casual riders into annual members.

+
+
+

1.2 Business Task

+

Primary objective: Develop data-driven recommendations for converting +casual riders to annual members

+
+

Focus areas:

+
    +
  • Identify distinct usage patterns between member types
    • +
  • Understand casual riders’ preferences and behaviors
    • +
  • Discover opportunities for targeted conversion strategies
    • +
+
+
+
+

1.3 Stakeholders

+
    +
  • Lily Moreno: Director of Marketing
    • +
  • Cyclistic Marketing Analytics Team
    • +
  • Cyclistic Executive Team
    • +
+
+
+
+

2. Data Preparation

+
+

2.1 Data Overview

+

This analysis uses Cyclistic bike-share data from December 2023 to +November 2024. The dataset contains over 5.9 million rides with detailed +information about each trip.

+
## Rows: 5,907,256
+## Columns: 14
+## $ ride_id            <chr> "C9BD54F578F57246", "CDBD92F067FA620E", "ABC0858E52…
+## $ rideable_type      <fct> electric_bike, electric_bike, electric_bike, electr…
+## $ started_at         <dttm> 2023-12-02 18:44:01, 2023-12-02 18:48:19, 2023-12-…
+## $ ended_at           <dttm> 2023-12-02 18:47:51, 2023-12-02 18:54:48, 2023-12-…
+## $ start_station_name <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
+## $ start_station_id   <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
+## $ end_station_name   <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
+## $ end_station_id     <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
+## $ start_lat          <dbl> 41.92, 41.92, 41.89, 41.95, 41.92, 41.91, 41.99, 42…
+## $ start_lng          <dbl> -87.66, -87.66, -87.62, -87.65, -87.64, -87.63, -87…
+## $ end_lat            <dbl> 41.92, 41.89, 41.90, 41.94, 41.93, 41.88, 42.00, 41…
+## $ end_lng            <dbl> -87.66, -87.64, -87.64, -87.65, -87.64, -87.65, -87…
+## $ member_casual      <fct> member, member, member, member, member, member, mem…
+## $ month_year         <dttm> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
+ + + + + + + + + + + + + + + + + + + + +
+Dataset Overview +
+Total Rides + +Unique Stations + +Date Range + +Member Rides + +Casual Rides +
+5907256 + +1823 + +December 01, 2023 to November 30, 2024 + +3741943 + +2165313 +
+
+
+

2.2 Data Quality Assessment

+

I conducted a comprehensive data quality assessment to ensure +reliable analysis:

+ + + + + + + + + + + + + + + + + + + + + + +
+Data Quality Metrics +
+Missing Station Names + +Missing Coordinates + +Invalid Durations + +Duplicate Rides + +% Missing Stations + +% Valid Coordinates +
+1661814 + +7341 + +778 + +1198 + +18.29347 + +99.87573 +
+
+
+

2.3 Data Cleaning Process

+

The cleaning process included:

+
    +
  1. Geographic Validation +
      +
    • Defined Chicago boundaries (41.6°N to 42.1°N, 87.9°W to 87.5°W)
      • +
    • Removed rides outside service area
      • +
    • Calculated ride distances using Haversine formula
      • +
    2. +
  2. Temporal Cleaning +
      +
    • Removed rides with invalid durations
      • +
    • Filtered out rides >24 hours or <1 minute
      • +
    • Standardized timestamps
      • +
    3. +
  3. Feature Engineering +
      +
    • Created time-based features (day, month, season)
      • +
    • Added ride categories (commute, leisure, etc.)
      • +
    • Calculated derived metrics (speed, distance)
      • +
    4. +
+ + + + + + + + + + + + + + + + + + + + + + + + + + +
+Impact of Data Cleaning +
+Metric + +Value +
+Initial Rows + +5907256.00 +
+Final Rows + +5758127.00 +
+Rows Removed + +149129.00 +
+% Data Retained + +97.48 +
+
+
+
+

3. Analysis and Insights

+
+

3.1 Temporal Patterns

+
+

Daily Usage Patterns

+

+
+
Key Findings:
+
    +
  • Members show distinct commuting peaks at 8AM and 5PM
    • +
  • Casual riders peak during midday hours
    • +
  • Evening usage differs significantly between groups
    • +
+
+
+
+

Weekly Patterns

+

+
+
Insights:
+
    +
  • Weekend usage dominates casual riding patterns
    • +
  • Members maintain consistent weekday usage
    • +
  • Saturday shows highest overall system usage
    • +
+
+
+
+

Seasonal Variations

+

+
    +
  • Seasonal Patterns: Both member and casual riders +show peak usage during summer months, but a substantial drop for casual +riders in the fall
    • +
+
+
+
+

3.2 User Behavior Analysis

+
+

Usage Patterns by User Type

+

+
    +
  • Key Usage Patterns: Annual members predominantly +use Cyclistic bikes for commuting, with commute-related trips +representing the largest share of their rides. This is evident in their +consistent usage during peak commuting hours (morning and evening rush). +In contrast, casual riders show a strong preference for leisure +activities, with a higher proportion of rides occurring during weekends +and midday hours. This suggests that casual riders are more likely to +use the bikes for recreational purposes or exploring the city.
    • +
+
+
+

Trip Characteristics

+

+
    +
  • Trip Duration and Distance: Members have a +relatively shorter average ride duration and distance, while casual +riders have a slightly wider distribution, which suggests casual riders +explore a variety of routes and stations
    • +
+
+
+
+

3.3 Geographic Analysis

+

+
+

Station Usage Patterns:

+
    +
  • Popular member stations cluster near business districts
    • +
  • Casual riders frequent tourist areas
    • +
  • Station utilization varies significantly by time of day
    • +
+
+
+
+
+

4. Key Findings and Recommendations

+
+

4.1 Primary Insights

+
    +
  1. Usage Patterns +
      +
    • Members primarily use bikes for commuting (63% of member rides +during rush hours)
      • +
    • Casual riders show strong weekend preference (47% of casual rides on +weekends)
      • +
    • Seasonal usage varies significantly for casual riders
      • +
    2. +
  2. Trip Characteristics +
      +
    • Members take shorter, more direct routes
      • +
    • Casual riders show more exploratory behavior
      • +
    • Round trips more common among casual riders
      • +
    3. +
  3. Geographic Preferences +
      +
    • Members concentrate around business districts
      • +
    • Casual riders cluster near tourist attractions
      • +
    • Station preference varies by time of day
      • +
    4. +
+
+
+

4.2 Recommendations

+
    +
  1. Targeted Commuter Conversion Program +
      +
    • Identify casual riders who regularly ride during commute hours
      • +
    • Offer special “Commuter Trial” membership
      • +
    • Highlight cost savings for regular commuters
      • +
    2. +
  2. Weekend-to-Weekday Extension Strategy +
      +
    • Create “Weekend Plus” membership tier
      • +
    • Offer graduated discounts for weekday rides
      • +
    • Partner with local attractions
      • +
    +Metrics for Success: +
      +
    • Weekend-to-weekday conversion rate
      • +
    • Membership upgrade rate
      • +
    • Partner location usage
      • +
    3. +
  3. Seasonal Retention Program +
      +
    • Implement early-bird winter discounts
      • +
    • Create seasonal challenges and rewards
      • +
    • Provide weather protection guarantees
      • +
    4. +
+
+
+
+

5. Implementation and Next Steps

+
+

5.1 Action Plan

+
    +
  1. Immediate Actions (Q1 2025) +
      +
    • Launch Commuter Trial Program
      • +
    • Develop mobile app features for tracking rewards
      • +
    • Establish partnership agreements
      • +
    2. +
  2. Medium-term Goals (Q2-Q3 2025) +
      +
    • Roll out seasonal challenges
      • +
    • Implement technology improvements
      • +
    • Expand station coverage in key areas
      • +
    3. +
  3. Long-term Objectives (Q4 2025+) +
      +
    • Full loyalty program integration
      • +
    • Dynamic pricing system
      • +
    • Predictive maintenance implementation
      • +
    4. +
+
+
+

5.2 Success Metrics

+
+

Track the following KPIs:

+
    +
  • Conversion rate from casual to annual members
    • +
  • Retention rate of converted members
    • +
  • Usage patterns of new members
    • +
  • Revenue per user
    • +
  • Customer satisfaction scores
    • +
+
+
+
+

5.3 Limitations and Future Research

+
+

Current Limitations:

+
    +
  • No individual user tracking across rides
    • +
  • Weather data not integrated
    • +
  • Limited demographic information
    • +
  • No pricing sensitivity data
    • +
+
+
+

Future Research Opportunities:

+
    +
  • Impact of weather on ridership
    • +
  • Price elasticity study
    • +
  • Demographic analysis
    • +
  • Multi-city comparison study
    • +
+
+
+
+ + + +
+
+ +
+ + + + + + + + + + + + + + + + +