Analysis Potential Customer Bank Portugal
Ana Sofia Noviandari
April 5, 2021
bank <- read.csv("bank-full.csv", sep = ";")
head(bank)## age job marital education default balance housing loan contact day
## 1 58 management married tertiary no 2143 yes no unknown 5
## 2 44 technician single secondary no 29 yes no unknown 5
## 3 33 entrepreneur married secondary no 2 yes yes unknown 5
## 4 47 blue-collar married unknown no 1506 yes no unknown 5
## 5 33 unknown single unknown no 1 no no unknown 5
## 6 35 management married tertiary no 231 yes no unknown 5
## month duration campaign pdays previous poutcome y
## 1 may 261 1 -1 0 unknown no
## 2 may 151 1 -1 0 unknown no
## 3 may 76 1 -1 0 unknown no
## 4 may 92 1 -1 0 unknown no
## 5 may 198 1 -1 0 unknown no
## 6 may 139 1 -1 0 unknown nostr(bank)## 'data.frame': 45211 obs. of 17 variables:
## $ age : int 58 44 33 47 33 35 28 42 58 43 ...
## $ job : chr "management" "technician" "entrepreneur" "blue-collar" ...
## $ marital : chr "married" "single" "married" "married" ...
## $ education: chr "tertiary" "secondary" "secondary" "unknown" ...
## $ default : chr "no" "no" "no" "no" ...
## $ balance : int 2143 29 2 1506 1 231 447 2 121 593 ...
## $ housing : chr "yes" "yes" "yes" "yes" ...
## $ loan : chr "no" "no" "yes" "no" ...
## $ contact : chr "unknown" "unknown" "unknown" "unknown" ...
## $ day : int 5 5 5 5 5 5 5 5 5 5 ...
## $ month : chr "may" "may" "may" "may" ...
## $ duration : int 261 151 76 92 198 139 217 380 50 55 ...
## $ campaign : int 1 1 1 1 1 1 1 1 1 1 ...
## $ pdays : int -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ previous : int 0 0 0 0 0 0 0 0 0 0 ...
## $ poutcome : chr "unknown" "unknown" "unknown" "unknown" ...
## $ y : chr "no" "no" "no" "no" ...summary(bank)## age job marital education
## Min. :18.00 Length:45211 Length:45211 Length:45211
## 1st Qu.:33.00 Class :character Class :character Class :character
## Median :39.00 Mode :character Mode :character Mode :character
## Mean :40.94
## 3rd Qu.:48.00
## Max. :95.00
## default balance housing loan
## Length:45211 Min. : -8019 Length:45211 Length:45211
## Class :character 1st Qu.: 72 Class :character Class :character
## Mode :character Median : 448 Mode :character Mode :character
## Mean : 1362
## 3rd Qu.: 1428
## Max. :102127
## contact day month duration
## Length:45211 Min. : 1.00 Length:45211 Min. : 0.0
## Class :character 1st Qu.: 8.00 Class :character 1st Qu.: 103.0
## Mode :character Median :16.00 Mode :character Median : 180.0
## Mean :15.81 Mean : 258.2
## 3rd Qu.:21.00 3rd Qu.: 319.0
## Max. :31.00 Max. :4918.0
## campaign pdays previous poutcome
## Min. : 1.000 Min. : -1.0 Min. : 0.0000 Length:45211
## 1st Qu.: 1.000 1st Qu.: -1.0 1st Qu.: 0.0000 Class :character
## Median : 2.000 Median : -1.0 Median : 0.0000 Mode :character
## Mean : 2.764 Mean : 40.2 Mean : 0.5803
## 3rd Qu.: 3.000 3rd Qu.: -1.0 3rd Qu.: 0.0000
## Max. :63.000 Max. :871.0 Max. :275.0000
## y
## Length:45211
## Class :character
## Mode :character
##
##
## library(ggplot2)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggforce)
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──## ✓ tibble 3.0.5 ✓ purrr 0.3.4
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()ggplot(data = bank, aes(x= age,))+
geom_histogram(bins = 35, binwidth = 4, color = "black", fill = "maroon" )+
labs(title="Customer Age Distribution",x="Age(years)", y = "Count",
subtitle = "yellow line indicate average Age")+
scale_x_continuous(breaks = seq(0,100,10))+
geom_vline(xintercept = mean(bank$age), color = "yellow", linetype = 5)
ggplot(bank, aes(x= marital, y = housing))+
geom_col(fill= "blue")+
ggtitle("Housing and Marital")
ggplot(data = bank, aes(x=education))+
geom_bar(fill = "dark blue")+ ggtitle("Subscription based on Education Level")+
xlab(" Education Level")+
guides(fill=guide_legend(title="Subscription of Term Deposit"))
ggplot(bank, aes(x=duration, y=balance)) +
facet_grid(cols = vars(y)) +
geom_point(shape=1, color = "purple")+
ggtitle("Duration VS Balance")
bank %>%
group_by(education, job) ## # A tibble: 45,211 x 17
## # Groups: education, job [48]
## age job marital education default balance housing loan contact day
## <int> <chr> <chr> <chr> <chr> <int> <chr> <chr> <chr> <int>
## 1 58 mana… married tertiary no 2143 yes no unknown 5
## 2 44 tech… single secondary no 29 yes no unknown 5
## 3 33 entr… married secondary no 2 yes yes unknown 5
## 4 47 blue… married unknown no 1506 yes no unknown 5
## 5 33 unkn… single unknown no 1 no no unknown 5
## 6 35 mana… married tertiary no 231 yes no unknown 5
## 7 28 mana… single tertiary no 447 yes yes unknown 5
## 8 42 entr… divorc… tertiary yes 2 yes no unknown 5
## 9 58 reti… married primary no 121 yes no unknown 5
## 10 43 tech… single secondary no 593 yes no unknown 5
## # … with 45,201 more rows, and 7 more variables: month <chr>, duration <int>,
## # campaign <int>, pdays <int>, previous <int>, poutcome <chr>, y <chr>ggplot(bank, aes(education, balance, fill = job ))+
geom_bar(stat="identity", position = "dodge")+
scale_fill_brewer(palette = "Paired")
bank <- bank %>%
mutate(age_group=
case_when(
age > 20 & age <= 25 ~ "20-25",
age > 25 & age <= 30 ~ "25-30",
age > 30 & age <= 35 ~ "30-35",
age > 35 & age <= 40 ~ "35-40",
age > 40 & age <= 45 ~ "40-45",
age > 45 & age <= 50 ~ "45-50",
age > 50 & age <= 55 ~ "50-55",
age > 55 ~ "above 55"
)
) %>%
count(age_group, loan)
# calculate the start and end angles for each pie
bank_pies <- left_join(bank,
bank %>%
group_by(age_group) %>%
summarize(n_total = sum(n))) %>%
group_by(age_group) %>%
mutate(end_angle = 2*pi*cumsum(n)/n_total, # ending angle for each pie slice
start_angle = lag(end_angle, default = 0), # starting angle for each pie slice
mid_angle = 0.5*(start_angle + end_angle)) # middle of each pie slice, for the text label## Joining, by = "age_group"rpie = 1 # pie radius
rlabel = 0.6 * rpie # radius of the labels; a number slightly larger than 0.5 seems to work better,
# but 0.5 would place it exactly in the middle as the question asks for.ks for.
# draw the pies
ggplot(bank_pies) +
geom_arc_bar(aes(x0 = 0, y0 = 0, r0 = 0, r = rpie,
start = start_angle, end = end_angle, fill = loan)) +
geom_text(aes(x = rlabel*sin(mid_angle), y = rlabel*cos(mid_angle), label = n),
hjust = 0.5, vjust = 0.5) +
coord_fixed() +
scale_x_continuous(limits = c(-1, 1), name = "", breaks = NULL, labels = NULL) +
scale_y_continuous(limits = c(-1, 1), name = "", breaks = NULL, labels = NULL) +
facet_wrap(~age_group)+
ggtitle("Loan By Age Group")
bank## age_group loan n
## 1 20-25 no 1063
## 2 20-25 yes 176
## 3 25-30 no 4694
## 4 25-30 yes 1000
## 5 30-35 no 8327
## 6 30-35 yes 1550
## 7 35-40 no 6633
## 8 35-40 yes 1177
## 9 40-45 no 5061
## 10 40-45 yes 985
## 11 45-50 no 4277
## 12 45-50 yes 916
## 13 50-55 no 3549
## 14 50-55 yes 806
## 15 above 55 no 4269
## 16 above 55 yes 631
## 17 <NA> no 94
## 18 <NA> yes 3ggplot(bank, aes(x=age_group, y= bank$balance, fill=age_group)) +
geom_boxplot() +
theme(
plot.title = element_text(size=14),
) +
ggtitle("Balance by Age Group") +
xlab("Years")+
ylab("Balance")## Warning: Use of `bank$balance` is discouraged. Use `balance` instead.
#Conclusions
there is some insight that we can get from the plots:
- The Customers with married marital status has more tendencies to housing
- The Most Subscriptions Customers who have background secondary of education level and the next position will be following by tertiary and then primary education levels
- we can get the insight from plot Duration VS Balance:
- The Customers with higher balance has shorter duration call to decides for subscription,
- The Customers who have a smaller balance needs extended duration call to decide on subscription,
- The Customers who do not want for a subscription they have shorter duration call then customers that going to say Yes to the subscription
The insight from the plot Balance, Job, and education level, that shows the customer with the highest balance has a job in management field with tertiary education level and the customer with the lowest balances who has a job as a student with primary education level
The Loan by Age plot shows Segmentation of Loan Customers by Age, Borrowers in Age Group 30-35 years is the highest group for the loan debt, And the second position of loan debt with adults aged 35 to 40, and the third position following by age 25-30 years old.
The last plot shows the older individuals are likely to have higher balances in their savings accounts