Code
library(readr)
library(dplyr)
library(tidyr)
library(scales)
library(ggplot2)Project 2 — Data Tidying
IMPORT LIBRARIES
DATA SOURCES
Code
## 1.NY HOUSING DATA - https://www.kaggle.com/datasets/nelgiriyewithana/new-york-housing-market
## 2.CARD ASSOCIATION ANALYSIS - Author-created illustrative data. Transaction counts and calculated percentages are hypothetical and are not actual card-network statistics.
## 3. TELECOMMUNICATION ANALYSIS - Author-created illustrative data. Transaction counts and calculated percentages are hypothetical and are not actual card-network statistics.IMPORTING DATASET 1 - NY HOUSING ANALYSIS
Code
origfile_url_ <- "https://raw.githubusercontent.com/MrKpoku/Data-Acquistion-and-Mangement---Kingsley-Kojo-Kpoku/refs/heads/main/PROJECT%202/Project%202%20-%20NY_Housing.csv"
ny_housing <- readr::read_csv("https://raw.githubusercontent.com/MrKpoku/Data-Acquistion-and-Mangement---Kingsley-Kojo-Kpoku/refs/heads/main/PROJECT%202/Project%202%20-%20NY_Housing.csv")
## Checking the data
head(ny_housing)# A tibble: 6 × 7
Year Month Bronx Brooklyn Manhattan Queens `Staten Island`
<dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
1 2024 Jan 565 948 1108 650 675
2 2024 Feb 568 952 1112 654 678
3 2024 Mar 572 958 1118 660 683
4 2024 Apr 575 965 1122 663 688
5 2024 May 579 972 1128 668 693
6 2024 Jun 582 978 1132 671 697CONVERTING THE COLUMNS
Code
ny_housing_long <- readr::read_csv(
"Project 2 - NY_Housing.csv",
show_col_types = FALSE
) |>
dplyr::mutate(
dplyr::across(
-c(Year, Month),
~ readr::parse_number(as.character(.x))
)
) |>
tidyr::pivot_longer(
cols = -c(Year, Month),
names_to = "Borough",
values_to = "Average_Price"
)
head(ny_housing_long)# A tibble: 6 × 4
Year Month Borough Average_Price
<dbl> <chr> <chr> <dbl>
1 2024 Jan Bronx 565
2 2024 Jan Brooklyn 948
3 2024 Jan Manhattan 1108
4 2024 Jan Queens 650
5 2024 Jan Staten Island 675
6 2024 Feb Bronx 568REMOVING NULL VALUES
Code
colSums(is.na(ny_housing_long)) Year Month Borough Average_Price
0 0 0 0 Code
ny_housing_clean <- ny_housing_long |>
dplyr::filter(!is.na(Average_Price))
ny_housing_clean <- na.omit(ny_housing_long)
ny_housing_clean <- ny_housing_long |>
dplyr::select(where(~ !all(is.na(.x))))
View(ny_housing_clean)
head(ny_housing_clean)# A tibble: 6 × 4
Year Month Borough Average_Price
<dbl> <chr> <chr> <dbl>
1 2024 Jan Bronx 565
2 2024 Jan Brooklyn 948
3 2024 Jan Manhattan 1108
4 2024 Jan Queens 650
5 2024 Jan Staten Island 675
6 2024 Feb Bronx 568MOST EXPENSIVE BOROUGH NY
Code
expensive_borough <- ny_housing_long |>
dplyr::group_by(Borough) |>
dplyr::summarise(
Average_Price = mean(Average_Price, na.rm = TRUE),
.groups = "drop"
) |>
dplyr::arrange(dplyr::desc(Average_Price))
expensive_borough# A tibble: 5 × 2
Borough Average_Price
<chr> <dbl>
1 Manhattan 1153.
2 Brooklyn 1000.
3 Staten Island 714.
4 Queens 687.
5 Bronx 595.Code
## the most expensive borough on average price is manhattan. COMPARE YoY GROWTH
Code
yearly_summary <- ny_housing_long |>
dplyr::group_by(Year, Borough) |>
dplyr::summarise(
Average_Price = mean(Average_Price, na.rm = TRUE),
.groups = "drop"
) |>
dplyr::arrange(Borough, Year) |>
dplyr::group_by(Borough) |>
dplyr::mutate(
YoY_Growth_Rate = (Average_Price / dplyr::lag(Average_Price) - 1) * 100
) |>
dplyr::ungroup() |>
dplyr::arrange(Year, dplyr::desc(Average_Price))
yearly_summary# A tibble: 10 × 4
Year Borough Average_Price YoY_Growth_Rate
<dbl> <chr> <dbl> <dbl>
1 2024 Manhattan 1130. NA
2 2024 Brooklyn 975 NA
3 2024 Staten Island 696. NA
4 2024 Queens 670. NA
5 2024 Bronx 581. NA
6 2025 Manhattan 1175. 3.93
7 2025 Brooklyn 1025. 5.15
8 2025 Staten Island 733. 5.44
9 2025 Queens 704 5.13
10 2025 Bronx 609. 4.84VISUALIZATION - YoY GROWTH RATE
Code
ggplot(yearly_summary, aes(x = Borough, y = YoY_Growth_Rate, fill = factor(Borough))) +
geom_col(position = "dodge") +
labs(
title = "YoY_Growth_Rate by Borough and Year",
x = "Borough",
y = "YoY_Growth_Rate",
fill = "Borough"
) +
theme_minimal()
Code
## there is an increase in the average prices on the boroughs through the years and what is expected. However based on the YOY Growth rate staten island had the fastest growth rate with 5.4.COMPARE MONTHLY AVERAGES
Code
month_order <- c(
"Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec"
)
monthly_summary <- ny_housing_long |>
dplyr::mutate(
Month = factor(Month, levels = month_order)
) |>
dplyr::group_by(Month, Borough) |>
dplyr::summarise(
Average_Price = mean(Average_Price, na.rm = TRUE),
.groups = "drop"
) |>
dplyr::arrange(Month, Borough)
monthly_summary# A tibble: 60 × 3
Month Borough Average_Price
<fct> <chr> <dbl>
1 Jan Bronx 580.
2 Jan Brooklyn 974.
3 Jan Manhattan 1130.
4 Jan Queens 669
5 Jan Staten Island 695
6 Feb Bronx 582.
7 Feb Brooklyn 978.
8 Feb Manhattan 1134
9 Feb Queens 672.
10 Feb Staten Island 698
# ℹ 50 more rowsVISUALIZATION - MONTHLY AVERAGES
Code
## GENERAL MONTHLY ANALYSIS
ggplot(
monthly_summary,
aes(x = Month, y = Average_Price, color = Borough, group = Borough)
) +
geom_line(linewidth = 1) +
geom_point(size = 2) +
labs(
title = "Average Housing Price by Month and Borough",
x = "Month",
y = "Average Price",
color = "Borough"
) +
theme_minimal()
Code
## 2024 ANALYSIS
month_order <- c(
"Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec"
)
ny_housing_long |>
dplyr::filter(Year == 2024) |>
dplyr::mutate(
Month = factor(Month, levels = month_order)
) |>
dplyr::group_by(Year, Month, Borough) |>
dplyr::summarise(
Average_Price = mean(Average_Price, na.rm = TRUE),
.groups = "drop"
) |>
ggplot2::ggplot(
ggplot2::aes(
x = Month,
y = Average_Price,
color = Borough,
group = Borough
)
) +
ggplot2::geom_line(linewidth = 1) +
ggplot2::geom_point(size = 2) +
ggplot2::labs(
title = "Average Housing Prices by Month — 2024",
x = "Month",
y = "Average Price",
color = "Borough"
) +
ggplot2::theme_minimal()
Code
## 2025 ANALYSIS
ny_housing_long |>
dplyr::filter(.data$Year == 2025) |>
dplyr::mutate(
Month = factor(
Month,
levels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
dplyr::group_by(Year, Month, Borough) |>
dplyr::summarise(
Average_Price = mean(Average_Price, na.rm = TRUE),
.groups = "drop"
) |>
ggplot2::ggplot(
ggplot2::aes(
x = Month,
y = Average_Price,
color = Borough,
group = Borough
)
) +
ggplot2::geom_line(linewidth = 1) +
ggplot2::geom_point(size = 2) +
ggplot2::labs(
title = "Average Housing Prices by Month — 2025",
x = "Month",
y = "Average Price",
color = "Borough"
) +
ggplot2::theme_minimal()
CONCLUSION AND ANALYTICS FINDING
1.Average housing prices increased across all five boroughs from 2024 to 2025. Staten Island had the highest year-over-year (YoY) growth rate at 5.4%, while Manhattan had the lowest. This shows that prices grew fastest in Staten Island in this data set; price growth alone does not show that more residents moved there.
2. Manhattan remains the most expensive borough, as expected, so customers considering it should plan for a higher budget and compare housing options carefully. Staten Island had the highest year-over-year growth rate in the sample, suggesting that its prices increased the fastest from 2024 to 2025 and may continue to attract buyer interest. These recommendations are based on simulated data, so customers should check current market information before making a real purchase.
3. Real estate Analyst Advice
As a real estate analyst, I would advise customers interested in Brooklyn to compare current properties with their budget and needs, and to consider acting sooner if they find a suitable property. In this sample, Brooklyn’s average prices rose over the period analyzed, which may indicate increasing costs for buyers if that pattern continues. However, the data shows past average prices, not future prices. Monthly averages can also change when the mix of properties sold changes—for example, if more high-priced homes sell in one month. Buyers should therefore consider individual property condition, location, financing costs, and recent comparable sales rather than relying on borough averages alone. Rising prices are not guaranteed to continue.
IMPORTING DATASET 2 - CARD ASSOCIATION ANALYSIS
Code
origfile_url_ <- "https://raw.githubusercontent.com/MrKpoku/Data-Acquistion-and-Mangement---Kingsley-Kojo-Kpoku/refs/heads/main/PROJECT%202/Card_Association_V1.csv"
card_association <- readr::read_csv("https://raw.githubusercontent.com/MrKpoku/Data-Acquistion-and-Mangement---Kingsley-Kojo-Kpoku/refs/heads/main/PROJECT%202/Card_Association_V1.csv")
## Checking the data
head(card_association)# A tibble: 6 × 16
month year visa_transactions_millions mastercard_transactions_millions
<chr> <dbl> <dbl> <dbl>
1 Jan 2025 200 100
2 Feb 2025 250 150
3 Mar 2025 100 120
4 Apr 2025 50 70
5 May 2025 80 100
6 Jun 2025 130 140
# ℹ 12 more variables: amex_transactions_millions <dbl>,
# discover_transactions_millions <dbl>, total_transactions_millions <dbl>,
# `visa_share_%` <dbl>, `mastercard_share_%` <dbl>, `amex_share_%` <dbl>,
# `discover_share_%` <dbl>, ...12 <lgl>, ...13 <lgl>, ...14 <lgl>,
# ...15 <lgl>, ...16 <lgl>CONVERTING THE COLUMNS
Code
card_association_2 <- card_association |>
pivot_longer(
cols = c(
visa_transactions_millions,
mastercard_transactions_millions,
amex_transactions_millions,
discover_transactions_millions
),
names_to = "network",
names_pattern = "(.*)_transactions_millions",
values_to = "transactions_millions"
) |>
mutate(
network = recode(
network,
visa = "Visa",
mastercard = "Mastercard",
amex = "American Express",
discover = "Discover"
)
) |>
select(
month,
year,
network,
transactions_millions
)
head(card_association_2)# A tibble: 6 × 4
month year network transactions_millions
<chr> <dbl> <chr> <dbl>
1 Jan 2025 Visa 200
2 Jan 2025 Mastercard 100
3 Jan 2025 American Express 150
4 Jan 2025 Discover 180
5 Feb 2025 Visa 250
6 Feb 2025 Mastercard 150EXPLORATORY ANALYSIS - NETWORK VS TRANSACTIONS
Code
network_totals <- card_association_2 |>
group_by(network) |>
summarise(
transactions_millions = sum(transactions_millions, na.rm = TRUE),
.groups = "drop"
) |>
mutate(
percent_contribution =
round(transactions_millions / sum(transactions_millions) * 100, 2),
transactions_millions = comma(transactions_millions, accuracy = 1)
) |>
arrange(desc(as.numeric(gsub(",", "", transactions_millions))))
network_totals# A tibble: 4 × 3
network transactions_millions percent_contribution
<chr> <chr> <dbl>
1 American Express 1,680 27.4
2 Discover 1,512 24.6
3 Visa 1,510 24.6
4 Mastercard 1,431 23.3VISUALIZATION - NETWORK VS TRANSACTIONS
Code
network_totals <- card_association_2 |>
group_by(network) |>
summarise(
transactions_millions = sum(transactions_millions, na.rm = TRUE),
.groups = "drop"
) |>
mutate(
percent_contribution =
transactions_millions / sum(transactions_millions) * 100
) |>
arrange(desc(transactions_millions))
ggplot(
network_totals,
aes(
x = reorder(network, transactions_millions),
y = transactions_millions,
fill = network
)
) +
geom_col(show.legend = FALSE) +
geom_text(
aes(
label = paste0(
comma(transactions_millions, accuracy = 1),
" (", round(percent_contribution, 2), "%)"
)
),
hjust = -0.1,
size = 3.5
) +
coord_flip() +
scale_y_continuous(
labels = comma,
expand = expansion(mult = c(0, 0.2))
) +
labs(
title = "Total Transactions by Card Network",
x = "Card network",
y = "Transactions (millions)"
) +
theme_minimal()
MONTHLY ANALYSIS ON TRANSACTIONS
Code
## GENERAL MONTH ON MONTH PERFORMANCE OF THE CARD ASSOCATIONS
monthly_growth <- card_association_2 |>
group_by(year, month) |>
summarise(
transactions_millions = sum(transactions_millions, na.rm = TRUE),
.groups = "drop"
) |>
mutate(
month_number = match(
month,
c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
arrange(year, month_number) |>
mutate(
previous_month_transactions = lag(transactions_millions),
mom_growth_pct = round(
(transactions_millions - previous_month_transactions) /
previous_month_transactions * 100,
2
)
) |>
select(
month,
previous_month_transactions,
mom_growth_pct
)
monthly_growth# A tibble: 13 × 3
month previous_month_transactions mom_growth_pct
<chr> <dbl> <dbl>
1 Jan NA NA
2 Feb 630 54.0
3 Mar 970 -48.4
4 Apr 500 -48
5 May 260 69.2
6 Jun 440 23.2
7 Jul 542 16.4
8 Aug 631 -28.7
9 Sep 450 -31.1
10 Oct 310 74.2
11 Nov 540 -25.9
12 Dec 400 15
13 <NA> 460 -100 Code
## LETS STUDY THE MoM ANALYSIS - AMERICAN EXPRESS CARD
amex_monthly_growth <- card_association_2 |>
filter(network == "American Express") |>
group_by(year, month) |>
summarise(
transactions_millions = sum(transactions_millions, na.rm = TRUE),
.groups = "drop"
) |>
mutate(
month_number = match(
month,
c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
arrange(year, month_number) |>
mutate(
previous_month_transactions = lag(transactions_millions),
mom_growth_pct =
(transactions_millions - previous_month_transactions) /
previous_month_transactions * 100
) |>
select(
month,
previous_month_transactions,
mom_growth_pct
)
amex_monthly_growth# A tibble: 13 × 3
month previous_month_transactions mom_growth_pct
<chr> <dbl> <dbl>
1 Jan NA NA
2 Feb 150 133.
3 Mar 350 -62.9
4 Apr 130 -53.8
5 May 60 100
6 Jun 120 25
7 Jul 150 33.3
8 Aug 200 -35
9 Sep 130 -30.8
10 Oct 90 0
11 Nov 90 0
12 Dec 90 33.3
13 <NA> 120 -100 Code
## LETS STUDY THE MoM ANALYSIS - DISCOVER CARD
discover_monthly_growth <- card_association_2 |>
filter(network == "Discover") |>
group_by(year, month) |>
summarise(
transactions_millions = sum(transactions_millions, na.rm = TRUE),
.groups = "drop"
) |>
mutate(
month_number = match(
month,
c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
arrange(year, month_number) |>
mutate(
previous_month_transactions = lag(transactions_millions),
mom_growth_pct =
(transactions_millions - previous_month_transactions) /
previous_month_transactions * 100
) |>
select(
month,
previous_month_transactions,
mom_growth_pct
)
discover_monthly_growth# A tibble: 13 × 3
month previous_month_transactions mom_growth_pct
<chr> <dbl> <dbl>
1 Jan NA NA
2 Feb 180 22.2
3 Mar 220 -31.8
4 Apr 150 -46.7
5 May 80 75
6 Jun 140 -12.9
7 Jul 122 -18.0
8 Aug 100 0
9 Sep 100 10
10 Oct 110 -9.09
11 Nov 100 -20
12 Dec 80 62.5
13 <NA> 130 -100 Code
## LETS STUDY THE MoM ANALYSIS - VISA CARD
visa_monthly_growth <- card_association_2 |>
filter(network == "Visa") |>
group_by(year, month) |>
summarise(
transactions_millions = sum(transactions_millions, na.rm = TRUE),
.groups = "drop"
) |>
mutate(
month_number = match(
month,
c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
arrange(year, month_number) |>
mutate(
previous_month_transactions = lag(transactions_millions),
mom_growth_pct =
(transactions_millions - previous_month_transactions) /
previous_month_transactions * 100
) |>
select(
month,
previous_month_transactions,
mom_growth_pct
)
visa_monthly_growth# A tibble: 13 × 3
month previous_month_transactions mom_growth_pct
<chr> <dbl> <dbl>
1 Jan NA NA
2 Feb 200 25
3 Mar 250 -60
4 Apr 100 -50
5 May 50 60
6 Jun 80 62.5
7 Jul 130 23.1
8 Aug 160 -37.5
9 Sep 100 -50
10 Oct 50 240
11 Nov 170 -29.4
12 Dec 120 -16.7
13 <NA> 100 -100 Code
## LETS STUDY THE MoM ANALYSIS - MASTERCARD
master_monthly_growth <- card_association_2 |>
filter(network == "Mastercard") |>
group_by(year, month) |>
summarise(
transactions_millions = sum(transactions_millions, na.rm = TRUE),
.groups = "drop"
) |>
mutate(
month_number = match(
month,
c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
arrange(year, month_number) |>
mutate(
previous_month_transactions = lag(transactions_millions),
mom_growth_pct =
(transactions_millions - previous_month_transactions) /
previous_month_transactions * 100
) |>
select(
month,
previous_month_transactions,
mom_growth_pct
)
master_monthly_growth# A tibble: 13 × 3
month previous_month_transactions mom_growth_pct
<chr> <dbl> <dbl>
1 Jan NA NA
2 Feb 100 50
3 Mar 150 -20
4 Apr 120 -41.7
5 May 70 42.9
6 Jun 100 40
7 Jul 140 22.1
8 Aug 171 -29.8
9 Sep 120 -50
10 Oct 60 200
11 Nov 180 -38.9
12 Dec 110 0
13 <NA> 110 -100 VISUALIZATION - MONTHLY ANALYSIS ON TRANSACTIONS
Code
## GENERAL PERFORMANCE ANALYSIS
monthly_growth |>
filter(!is.na(month), !is.na(mom_growth_pct)) |>
mutate(
month = factor(
month,
levels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
ggplot(aes(x = month, y = mom_growth_pct, group = 1)) +
geom_hline(yintercept = 0, color = "gray60", linetype = "dashed") +
geom_line(color = "#2878B5", linewidth = 1) +
geom_point(color = "#2878B5", size = 3) +
scale_y_continuous(labels = label_percent(scale = 1)) +
labs(
title = "Month-over-Month Transaction Growth",
x = "Month",
y = "Growth from previous month (%)"
) +
theme_minimal()
Code
## MoM AMERICAN EXPRESS VISUALIZATION PERFORMANCE
amex_monthly_growth |>
filter(!is.na(month), !is.na(mom_growth_pct)) |>
mutate(
month = factor(
month,
levels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
ggplot(aes(x = month, y = mom_growth_pct, group = 1)) +
geom_hline(yintercept = 0, color = "gray60", linetype = "dashed") +
geom_line(color = "#2878B5", linewidth = 1) +
geom_point(color = "#2878B5", size = 3) +
scale_y_continuous(labels = label_percent(scale = 1)) +
labs(
title = "AMEX Month-over-Month Transaction Growth",
x = "Month",
y = "Growth from previous month (%)"
) +
theme_minimal()
Code
## MoM DISCOVER CARD VISUALIZATION PERFORMANCE
discover_monthly_growth |>
filter(!is.na(month), !is.na(mom_growth_pct)) |>
mutate(
month = factor(
month,
levels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
ggplot(aes(x = month, y = mom_growth_pct, group = 1)) +
geom_hline(yintercept = 0, color = "gray60", linetype = "dashed") +
geom_line(color = "#2878B5", linewidth = 1) +
geom_point(color = "#2878B5", size = 3) +
scale_y_continuous(labels = label_percent(scale = 1)) +
labs(
title = "Discover Month-over-Month Transaction Growth",
x = "Month",
y = "Growth from previous month (%)"
) +
theme_minimal()
Code
## MoM VISA CARD VISUALIZATION PERFORMANCE
visa_monthly_growth |>
filter(!is.na(month), !is.na(mom_growth_pct)) |>
mutate(
month = factor(
month,
levels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
ggplot(aes(x = month, y = mom_growth_pct, group = 1)) +
geom_hline(yintercept = 0, color = "gray60", linetype = "dashed") +
geom_line(color = "#2878B5", linewidth = 1) +
geom_point(color = "#2878B5", size = 3) +
scale_y_continuous(labels = label_percent(scale = 1)) +
labs(
title = "Visa Month-over-Month Transaction Growth",
x = "Month",
y = "Growth from previous month (%)"
) +
theme_minimal()
Code
## MoM MASTERCARD VISUALIZATION PERFORMANCE
master_monthly_growth |>
filter(!is.na(month), !is.na(mom_growth_pct)) |>
mutate(
month = factor(
month,
levels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
)
) |>
ggplot(aes(x = month, y = mom_growth_pct, group = 1)) +
geom_hline(yintercept = 0, color = "gray60", linetype = "dashed") +
geom_line(color = "#2878B5", linewidth = 1) +
geom_point(color = "#2878B5", size = 3) +
scale_y_continuous(labels = label_percent(scale = 1)) +
labs(
title = "Mastercard Month-over-Month Transaction Growth",
x = "Month",
y = "Growth from previous month (%)"
) +
theme_minimal()
CONCLUSION AND ANALYTICS FINDING
1.American Express recorded the highest share of transactions at 27.39%, while Mastercard had the lowest share at 23.33%. The difference is 4.06 percentage points, so the distribution is relatively balanced across the card networks in this data set. No single network accounts for a dominant share of transactions, suggesting that the market is not concentrated in one network.
2. The month-over-month charts show that no card network had consistently positive growth across the year. All four networks experienced both increases and declines, with a notable spike in October for Visa and MasterCard. American Express had the largest visible increase in February, followed by a sharp decline in March. Discover’s changes appear less extreme than the others overall, though it also had sizable increases in May and December.
3.Based on month-over-month growth, American Express and Discover showed strong gains in some months, while Visa and MasterCard had especially large October increases.
IMPORTING DATASET 3 - TELECOMMUNICATION ANALYSIS
Code
## DATASET 3 - TELECOMMUNICATION ANALYSIS
origfile_url_ <- "https://raw.githubusercontent.com/MrKpoku/Data-Acquistion-and-Mangement---Kingsley-Kojo-Kpoku/refs/heads/main/PROJECT%202/Tele_Data.csv"
tele_comm <- readr::read_csv("https://raw.githubusercontent.com/MrKpoku/Data-Acquistion-and-Mangement---Kingsley-Kojo-Kpoku/refs/heads/main/PROJECT%202/Tele_Data.csv")
## Checking the data
head(tele_comm)# A tibble: 6 × 17
customer_id Customer_Name Gender `Monthly Charges` Churn Jan Feb Mar
<dbl> <chr> <chr> <dbl> <chr> <dbl> <dbl> <dbl>
1 101 Kingsley Male 29.8 Yes 12 15 11
2 102 Patricia Female 57.0 No 8 10 9
3 103 Jasmine Female 53.8 No 9 7 15
4 104 Donald Male 42.3 No 12 4 6
5 105 Juliet Female 70.7 Yes 11 14 16
6 106 Kian Male 99.6 No 11 11 12
# ℹ 9 more variables: Apr <dbl>, May <dbl>, Jun <dbl>, Jul <dbl>, Aug <dbl>,
# Sep <dbl>, Oct <dbl>, Nov <dbl>, Dec <dbl>CONVERTING THE COLUMNS
Code
tele_comm2 <- tele_comm %>%
pivot_longer(
cols = Jan:Dec,
names_to = "Months",
values_to = "Counts_Calls"
)
tele_comm2# A tibble: 168 × 7
customer_id Customer_Name Gender `Monthly Charges` Churn Months Counts_Calls
<dbl> <chr> <chr> <dbl> <chr> <chr> <dbl>
1 101 Kingsley Male 29.8 Yes Jan 12
2 101 Kingsley Male 29.8 Yes Feb 15
3 101 Kingsley Male 29.8 Yes Mar 11
4 101 Kingsley Male 29.8 Yes Apr 14
5 101 Kingsley Male 29.8 Yes May 12
6 101 Kingsley Male 29.8 Yes Jun 22
7 101 Kingsley Male 29.8 Yes Jul 14
8 101 Kingsley Male 29.8 Yes Aug 13
9 101 Kingsley Male 29.8 Yes Sep 11
10 101 Kingsley Male 29.8 Yes Oct 10
# ℹ 158 more rowsEXPLORATORY ANALYSIS
Code
names(tele_comm2)[1] "customer_id" "Customer_Name" "Gender" "Monthly Charges"
[5] "Churn" "Months" "Counts_Calls" Code
customer_summary <- tele_comm2 |>
group_by(Customer_Name, Gender, `Monthly Charges`, Churn) |>
summarise(
counts_calls = sum(Counts_Calls, na.rm = TRUE),
.groups = "drop"
)
## RENAMING CUSTOMER_NAME COLUMN TO EMPLOYEE_NAME
tele_comm2 <- tele_comm2 |>
rename(Employee_Name =Customer_Name)
tele_comm2 <- tele_comm2 |>
rename(Customer_Name =Employee_Name)
customer_summary# A tibble: 11 × 5
Customer_Name Gender `Monthly Charges` Churn counts_calls
<chr> <chr> <dbl> <chr> <dbl>
1 Alfred Male 105. Yes 170
2 Donald Male 42.3 No 147
3 Jasmine Female 53.8 No 194
4 Juliet Female 70.7 Yes 143
5 Kaira Female 89.1 Yes 162
6 Kian Male 99.6 No 177
7 Kingsley Male 29.8 Yes 173
8 Obed Male 29.8 No 182
9 Patricia Female 57.0 No 191
10 Renee Female 56.2 Yes 180
11 <NA> <NA> NA <NA> 0Code
## CUSTOMER_NAME VS COUNTS_CALLS ANALYSIS
customer_call_totals <- tele_comm2 |>
group_by(Customer_Name) |>
summarise(
total_calls = sum(Counts_Calls, na.rm = TRUE),
.groups = "drop"
) |>
arrange(desc(total_calls))
customer_call_totals# A tibble: 11 × 2
Customer_Name total_calls
<chr> <dbl>
1 Jasmine 194
2 Patricia 191
3 Obed 182
4 Renee 180
5 Kian 177
6 Kingsley 173
7 Alfred 170
8 Kaira 162
9 Donald 147
10 Juliet 143
11 <NA> 0Code
## jasmine recorded the highest number of calls made for the company. considerations should be made to reward her
## GENDER VS MONTHLY CHARGES ANALYSIS
gender_charges <- tele_comm2 |>
group_by(Gender) |>
summarise(
average_monthly_charge = mean(`Monthly Charges`, na.rm = TRUE),
.groups = "drop"
) |>
arrange(desc(average_monthly_charge))
gender_charges# A tibble: 3 × 2
Gender average_monthly_charge
<chr> <dbl>
1 Female 65.4
2 Male 61.3
3 <NA> NaN Code
## averagely females paid more charges to the telcos than males.can you base this on movies ? VISUALIZATIONS
Code
## CUSTOMER_NAME VS COUNTS_CALLS ANALYSIS
ggplot(
customer_call_totals,
aes(
x = reorder(Customer_Name, total_calls),
y = total_calls
)
) +
geom_col(fill = "#2878B5") +
coord_flip() +
labs(
title = "Total Calls by Customer",
x = "Customer",
y = "Total calls"
) +
theme_minimal()
Code
## GENDER VS MONTHLY CHARGES ANALYSIS
ggplot(
gender_charges,
aes(
x = reorder(Gender, average_monthly_charge),
y = average_monthly_charge,
fill = Gender
)
) +
geom_col(show.legend = FALSE) +
geom_text(
aes(label = sprintf("$%.2f", average_monthly_charge)),
hjust = -0.15
) +
coord_flip() +
scale_y_continuous(
labels = scales::dollar_format(),
expand = expansion(mult = c(0, 0.15))
) +
labs(
title = "Average Monthly Charges by Gender",
x = "Gender",
y = "Average monthly charge (USD)"
) +
theme_minimal()
CONCLUSION AND ANALYTICS FINDING
Kingsley Connect Telecom should use these findings to explore customer engagement and plan value. Jasmine’s high call activity may make her a good candidate for a loyalty incentive, such as bonus minutes or a reward for continued use. The company could also test introductory calling bundles for customers with low call activity, while first checking whether those customers use other services or simply prefer different ways to communicate. Incentives should be evaluated to see whether they increase call activity and customer retention.
Female customers had higher average monthly charges than male customers in this sample. This could reflect differences in subscribed plans, service add-ons, data use, or customer mix, but the current analysis does not establish the reason. Kingsley Connect Telecom should compare those factors across groups before making pricing or marketing decisions, and ensure offers are based on customer needs and service usage rather than assumptions about gender.
These recommendations are starting points for further analysis. The results cover the customers and period in the dataset, so they should not be treated as proof of broader customer behavior without checking the sample size, time period, and underlying billing details.