1. Introduction

This case evaluates Cyclistic bike-share product for a fictional company, Cyclistic.

The main objective in this analysis was to evaluate the behavior of two types of users of Cyclist services, member users that have a annual membership plan and casual users that acquire single rides. It was evaluated different parameters such as ride type (classic, electrical, docked), ride duration, weekday, month, hour of the day. Considering this variables, it was observed different behaviors in this two type of users in order to give a direction for Marketing team to increase the member users.

2. Background and Context

Cyclistic, a successful bike-share company in Chicago, operates over 5,800 bikes and 600 docking stations geotracked and locked in a network citywide. The bikes are interchangeable across stations, offering flexibility to users.

Distinguishing itself by providing reclining bikes, hand tricycles, and cargo bikes, Cyclistic aims to be inclusive to those with disabilities and riders unable to use standard two-wheeled bikes. While most riders prefer traditional bikes, 8% use assistive options. Cyclistic’s user base enjoys leisure rides, with 30% utilizing bikes for daily commutes. The type of users are casual riders that buy single-ride or full-day passes, while members enjoy Cyclistic’s membership with annual plan.

Financial analysis reveals that annual members are more profitable. Despite the success of pricing plans, maximizing annual memberships is crucial for future growth. Rather than targeting new customers, the goal is to convert existing casual riders who are already familiar with Cyclistic.

The marketing team objective is to develop marketing strategies to convert casual riders into annual members. To achieve this, the team needs a deeper understanding of the differences between annual members and casual riders, motivations for casual riders to buy a membership, and the impact of digital media on marketing tactics.

3. Problem Statement

For this case the objective is to have a better understanding of different behaviors between members and casual riders, in order to achieve the strategic plan for converting casual riders to member riders.

Therefore, the problem statement that will be answered is:

How do annual members and casual riders use Cyclistic bikes differently?

4. Prepare

4.1 Data Upload

All data was made available in the case study for Google Data Analytics Capstone Course by Motivate International Inc.

Data was download and stored locally in the link https://divvy-tripdata.s3.amazonaws.com/index.html.

The data license can be found here https://divvybikes.com/data-license-agreement.

For the analysis, it was download and evaluated the data from August-2021 to July-2023.

Load raw data from local file. Upload of data can be checked in details in append.

load(file="./tripdf_rawdata.Rda") 

4.2 Packages

packages <- c("ggplot2", "dplyr","geosphere","tidyverse","knitr")
lapply(packages, require, character.only = TRUE)
Sys.setlocale("LC_TIME", "en_US") #Change language to English
rm(packages)

4.3 Data Description

Data description:

str(tripdf_rawdata)
## 'data.frame':    11625069 obs. of  13 variables:
##  $ ride_id           : chr  "99103BB87CC6C1BB" "EAFCCCFB0A3FC5A1" "9EF4F46C57AD234D" "5834D3208BFAF1DA" ...
##  $ rideable_type     : chr  "electric_bike" "electric_bike" "electric_bike" "electric_bike" ...
##  $ started_at        : chr  "2021-08-10 17:15:49" "2021-08-10 17:23:14" "2021-08-21 02:34:23" "2021-08-21 06:52:55" ...
##  $ ended_at          : chr  "2021-08-10 17:22:44" "2021-08-10 17:39:24" "2021-08-21 02:50:36" "2021-08-21 07:08:13" ...
##  $ start_station_name: chr  "" "" "" "" ...
##  $ start_station_id  : chr  "" "" "" "" ...
##  $ end_station_name  : chr  "" "" "" "" ...
##  $ end_station_id    : chr  "" "" "" "" ...
##  $ start_lat         : num  41.8 41.8 42 42 41.8 ...
##  $ start_lng         : num  -87.7 -87.7 -87.7 -87.7 -87.6 ...
##  $ end_lat           : num  41.8 41.8 42 42 41.8 ...
##  $ end_lng           : num  -87.7 -87.6 -87.7 -87.7 -87.6 ...
##  $ member_casual     : chr  "member" "member" "member" "member" ...

Data summary:

summary(tripdf_rawdata)
##    ride_id          rideable_type       started_at          ended_at        
##  Length:11625069    Length:11625069    Length:11625069    Length:11625069   
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##                                                                             
##  start_station_name start_station_id   end_station_name   end_station_id    
##  Length:11625069    Length:11625069    Length:11625069    Length:11625069   
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##                                                                             
##    start_lat       start_lng         end_lat         end_lng      
##  Min.   :41.64   Min.   :-87.92   Min.   : 0.00   Min.   :-88.97  
##  1st Qu.:41.88   1st Qu.:-87.66   1st Qu.:41.88   1st Qu.:-87.66  
##  Median :41.90   Median :-87.64   Median :41.90   Median :-87.64  
##  Mean   :41.90   Mean   :-87.65   Mean   :41.90   Mean   :-87.65  
##  3rd Qu.:41.93   3rd Qu.:-87.63   3rd Qu.:41.93   3rd Qu.:-87.63  
##  Max.   :45.64   Max.   :-73.80   Max.   :42.37   Max.   :  0.00  
##                                   NA's   :11692   NA's   :11692   
##  member_casual     
##  Length:11625069   
##  Class :character  
##  Mode  :character  
##                    
##                    
##                    
## 
# NA values
na_summary <- sapply(tripdf_rawdata, function(x) sum(is.na(x))) #NA count per column

# Empty Values
empty_summary <- sapply(tripdf_rawdata, function(x) length(which(x == ""))) #Distinct count per column

# Distinct observations
dis_summary <- sapply(tripdf_rawdata, function(x) n_distinct(x)) #Distinct count per column
  • NA: maximum NA in one column values represents 0.1 % of total data - Insignificant cases with NA values

  • Empty Values represents 15.87 % of data in one variable.

    • 100% of this data were in were in variables with station name and station id, both in start and end trip.
    • Also 100% of the missing date were on electric bikes.
  • Data also shows different station names for the same station id.

5. Process

5.1 Data Cleaning

The following tasks were done in the raw data: - Filter out observations with NA values. - Transform date class of started_at column. - Create columns for months, hour of the day that the ride started, weekday of the ride, and ride duration in minutes. - Remove latitude and longitude columns.

tripdf_tidydata <- tripdf_rawdata %>% filter(complete.cases(.))
tripdf_tidydata$started_at <- as.POSIXct(tripdf_tidydata$started_at)
tripdf_tidydata$date <- as.Date(tripdf_tidydata$started_at, tz = "EST")
tripdf_tidydata <- tripdf_tidydata %>%
  mutate(month = format(started_at, "%Y-%m"),
         hour = lubridate::hour(started_at),
         weekday = weekdays(started_at), 
         ride_duration_min = as.double(difftime(ended_at,started_at, units="mins")))
tripdf_tidydata$member_casual <- as.factor(tripdf_tidydata$member_casual)
tripdf_tidydata$rideable_type <- as.factor(tripdf_tidydata$rideable_type)
tripdf_tidydata$weekday <- factor(tripdf_tidydata$weekday, levels=c("Sunday", "Monday", "Tuesday","Wednesday","Thursday","Friday","Saturday"))
tripdf_tidydata <- tripdf_tidydata %>% 
  mutate(weekday_type = case_when(weekday == 'Sunday' | weekday == 'Saturday' ~ 'Weekend', .default = 'Weekday'))
tripdf_tidydata <- tripdf_tidydata %>% 
  select(-start_lat,-start_lng,-end_lat,-end_lng)
tripdf_tidydata_full <- tripdf_tidydata

5.2 Filter

In order to check the necessity of using all the two years period data, a preliminary exploratory analysis was done to evaluate the trend of quantity of rides per type of user in this period.

  ## Preliminary Exploratory Analysis
  trips_monthly  <- tripdf_tidydata_full %>%
    select(month,member_casual) %>%
    group_by(month,member_casual) %>%
    summarise(count = n())
  
  ggplot(trips_monthly,aes(x=month, y=count/1000, group = member_casual, color = member_casual)) + 
    geom_line()+geom_point() +
    theme(axis.text.x = element_text(face = "bold",angle=90),
          legend.position="bottom",
          legend.title = element_blank()) +
    ylab("Rides (*10^3)]")+xlab("")

There is a cyclical trend for both type of users, with a higher decrease of casual riders in winter season, December to February. It will be narrowed the data for just a one year period. Furthermore, it will be removed outliers from rides duration.

tripdf_tidydata <- tripdf_tidydata %>%
  filter(date >= '2022-08-01') %>% 
  filter(ride_duration_min >= 1 & ride_duration_min <= 120)

6. Analyze

Split of type of user per bike type. Casual riders have more preference for electric bikes, and member users don’t use docked bikes.

user_rideable_tbl <- table(tripdf_tidydata$rideable_type, tripdf_tidydata$member_casual)
user_rideable_tbl <- prop.table(user_rideable_tbl, margin = 2) * 100
user_rideable_df <- as.data.frame.matrix(user_rideable_tbl)
colnames(user_rideable_df) <- c("Casual (%)", "Member (%)")
print(round(user_rideable_df, 1))
##               Casual (%) Member (%)
## classic_bike        36.6       48.2
## docked_bike          5.5        0.0
## electric_bike       57.8       51.8
ggplot(tripdf_tidydata,aes(x=(member_casual), fill=rideable_type)) + 
  geom_bar(position = "stack")+xlab("")+ylab("Rides") +
  theme(axis.text.x = element_text(face = "bold"),
        legend.title = element_blank()) +
  scale_fill_brewer(palette = "Set1")

avgrides_per_wkday <- tripdf_tidydata %>%
  group_by(weekday,member_casual) %>%
  summarise(avg_rides = n() / n_distinct(date))

ggplot(avgrides_per_wkday, aes(x = weekday, y = avg_rides, fill = member_casual)) +
  geom_col(position = "dodge", alpha = 0.7) +
  labs(x = "",
       y = "Average of Rides per day",
       fill = "") +
  scale_fill_brewer(palette = "Set1") 

avg_wkdaytyp <- table(tripdf_tidydata$weekday_type, tripdf_tidydata$member_casual)
avg_wkdaytyp_per <- prop.table(avg_wkdaytyp, margin = 1) * 100
avg_wkdaytyp_per_df <- as.data.frame.matrix(avg_wkdaytyp_per)
colnames(avg_wkdaytyp_per_df) <- c("Casual (%)", "Member (%)")
print(round(avg_wkdaytyp_per_df, 1))
##         Casual (%) Member (%)
## Weekday       33.9       66.1
## Weekend       47.2       52.8

In average, casual users have higher riders than member users. The most common duration of ride duration is around 4 minutes and casual is 7 minutes. besides this difference the shape of the curve is really similar for both type of users.

#Function to find mode 
getmode <- function(v) {
  uniqv <- unique(v)
  uniqv[which.max(tabulate(match(v, uniqv)))]
}

ride_duration_df <- tripdf_tidydata %>%
  group_by(member_casual) %>%
  summarise(
    mean_duration = mean(ride_duration_min, na.rm = TRUE),
    Q1 = quantile(ride_duration_min, 0.25, na.rm = TRUE),
    median = quantile(ride_duration_min, 0.5, na.rm = TRUE),
    Q3 = quantile(ride_duration_min, 0.75, na.rm = TRUE),
    min_duration = min(ride_duration_min, na.rm = TRUE),
    max_duration = max(ride_duration_min, na.rm = TRUE),
    mode = getmode(ride_duration_min)
  )
print(ride_duration_df)
## # A tibble: 2 Ă— 8
##   member_casual mean_duration    Q1 median    Q3 min_duration max_duration  mode
##   <fct>                 <dbl> <dbl>  <dbl> <dbl>        <dbl>        <dbl> <dbl>
## 1 casual                 17.9  6.95  12     21.8            1          120  6.55
## 2 member                 11.8  5.18   8.73  14.8            1          120  4.32
ggplot(tripdf_tidydata, aes(x = ride_duration_min, fill = member_casual)) +
  geom_histogram(binwidth = 0.5, position = "identity", alpha = 0.7) +
  labs(title = "",
       x = "Ride Duration (min)",
       y = "",
       fill = "") + 
  xlim(0,50) + 
  scale_fill_brewer(palette = "Set1")

From the evaluation of day time for rides between the two types of user we can Members during weekdays concentred rides between 7:00 and 8:00, and also from 17:00 to 18:00. During weekends more disperse between 12:00 and 17:00, but much lower than weekdays.

# Count occurrences of each hour per weekday
hour_counts_member <- tripdf_tidydata %>% filter(member_casual == "member") %>%
  group_by(weekday, hour) %>%
  summarise(count = n())

# Create the heatmap
ggplot(hour_counts_member, aes(x = factor(weekday), y = hour, fill = count)) +
  geom_tile() +
  scale_fill_gradient(low = "white", high = "blue") +
  labs(title = "Member Rides Heatmap",
       x = "",
       y = "Day Time") +
  guides(fill = FALSE)+
  theme_minimal()

hour_counts_casual <- tripdf_tidydata %>% filter(member_casual == "casual") %>%
  group_by(weekday, hour) %>%
  summarise(count = n())

ggplot(hour_counts_casual, aes(x = factor(weekday), y = hour, fill = count)) +
  geom_tile() +
  scale_fill_gradient(low = "white", high = "blue") +
  labs(title = "Casual Rides Heatmap",
       x = "",
       y = "Day Time") +
  guides(fill = FALSE)+
  theme_minimal()

This trend during weekdays is interesting because shows some aspects that people use more or lower bike share product. Probably, this trips are to commute to work or school at 8:00 and 17:00. Casual riders probably use only to return (18:00). One indication is that this people don’t have a place to exchange clothes and prefer only to return.

commute_df <- tripdf_tidydata %>% 
  filter(weekday_type == 'Weekday' & ((hour >= 7 & hour <= 9) | (hour >= 16 & hour <= 18 ))) %>% 
  group_by(member_casual) %>%
  count()

total_df <- tripdf_tidydata %>%
  group_by(member_casual) %>%
  count()  

Conclusion

The behavior of each group can be defined as follow:

Member:

Uses electric and classic bike. Do more rides during weekdays to commute, during the morning from 7:00 to 9:00 and in the evening from 16:00 to 18:00. Around 36% of the rides from member users are to commute. Average of distance duration is around

Casual Uses more electric bikes than classic bikes. A small portion also uses docked bikes. The highest number of casual riders happens during the weekend. During week days it is observed a similar pattern of casual riders using to commute, but more expressive in the evening only. The variation of casual rides is much higher than member rides during the year. It is observed a reduction around XXX.

Takeaways

The most significant behavior that is observed is the difference of usage during weekdays and weekend between member and casual rides. Also the concentration of rides in some day time during the week days shows probably more usage for commute propose than leisure.

It is observed some difference between usage of

It would be nice to have a rider id information in order to get some information: - How is the average and dispersion of travels for members and casual riders - There are two types of casual riders: Casual that use to little (once/twice per month) and orders that have at least one ride per week?

Append

Data upload from local folder.

file_list <- list.files(path = "./Data/Excel_files", pattern = "*.csv", full.names = TRUE)

# Initialize an empty list to store the data frames
df_list <- list()

# Loop through each file and read it into a data frame
for(file in file_list) {
  df <- read.csv(file)
  df_list[[file]] <- df
}

# Combine all data frames into one
tripdf_rawdata <- do.call(rbind, df_list) #Raw data of all files
rm(df,df_list,file,file_list)