Regork is one of the largest retailers in the world. I was entrusted to find a way to build more profits and revenue for this retailer through Data Analysis.
I initially wanted to see what Regork struggled with in order to find a solution further in my analysis. Customers is what makes Regork gain its profits so I looked into the demographics section to see what demographic had to least amount of profits.
After question 1 this led me to see what item was purchased the most by this demographic. I wanted to look into that to see if Regork could offer coupons on this product in order to drive more consumers into their stores.
I received the data from household transactions from 2469 households. This data was based off of Regork 2017 sales.
I wanted to analyze the data to find anomalies on what Regork is struggling with as well as what they are doing good that is helping their business. I used graphs and data to visualize the data and spot the anomalies within the data.
With the help of my data and the information I have obtained throughout this descriptive analysis I’ve gained a couple of suggestions that can help build revenue for Regork. These suggestions are meant to help drive consumers into Regork and maximize the volume of consumers within this retailer.
These are the packages I used to help complete my analysis. These range from data information to helping make my analysis more visually pleasing.
completejourney - Gave me the data-set that I was analyzing.
ggplot2 - Provided me with the different graphs that I can use to plot the results.
dplyr - For flexibility in data manipulation.
tidyverse clean up messy data
library(completejourney)
## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.
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, union
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.0
## ✔ readr 2.1.5
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
The original data set is from the ‘completejourney’ package. This data set has the records of 2017 household level transactions of 2469 households who are frequent shoppers at Regork.
For this project I used this list of data sets to help me complete my analysis:
transactions <- get_transactions()
promotions <- get_promotions()
products <- products
demographics <- demographics
coupons <- coupons
coupon_redemptions <- coupon_redemptions
What age demographic produced the least amount of sales for Regork?
# Finding the underperforming demographic
Worst <- demographics %>%
inner_join(transactions, by = "household_id") %>%
group_by(age, income) %>%
summarise(total_sales = sum(sales_value)) %>%
filter(total_sales < 50000) %>%
arrange(total_sales)
## `summarise()` has grouped output by 'age'. You can override using the `.groups`
## argument.
ggplot(Worst, aes(x = age, y = total_sales)) +
geom_col(fill = "darkgreen") +
scale_x_discrete(guide = guide_axis(90)) +
labs(title = "Total Purchases by Age",
subtitle = "Data represents total sales from age group based on their income level",
x = "Age",
y = "Total Sales Value",
tag = "Fig.1")
What is the most sold product for 19-24 year olds? Should Regork offer some type of coupon for it?
Productss <- products %>%
inner_join(transactions, by = "product_id") %>%
group_by(product_category)%>%
summarize(total_qty= sum(quantity), total_sales =sum(sales_value))%>%
filter(total_sales <100 & total_qty <100)%>%
mutate(avg_rev = total_sales/total_qty)%>%
arrange(total_sales)
Productss
## # A tibble: 16 × 4
## product_category total_qty total_sales avg_rev
## <chr> <dbl> <dbl> <dbl>
## 1 TOYS 3 4.17 1.39
## 2 MISCELLANEOUS CROUTONS 1 6.39 6.39
## 3 NDAIRY/TEAS/JUICE/SOD 2 9.4 4.7
## 4 PROD SUPPLIES 12 19.7 1.64
## 5 BULK FOODS 4 20.1 5.02
## 6 PKG.SEAFOOD MISC 8 27.9 3.49
## 7 MISCELLANEOUS HBC 11 30.5 2.77
## 8 RW FRESH PROCESSED MEAT 17 30.8 1.81
## 9 EASTER LILY 2 32.0 16.0
## 10 HOME HEALTH CARE 4 49.5 12.4
## 11 PHARMACY 6 50.9 8.49
## 12 BOUQUET (NON ROSE) 7 53.9 7.70
## 13 RESTRICTED DIET 33 64.6 1.96
## 14 WATCHES/CALCULATORS/LOBBY 16 66.1 4.13
## 15 BOTTLE DEPOSITS 95 68.9 0.725
## 16 NATURAL HBC 22 84.1 3.82
ggplot(Productss, aes(x = product_category, y = total_sales)) +
geom_point(aes(color = avg_rev,size = total_qty), shape = 19) +
scale_x_discrete(guide = guide_axis(angle = 45)) +
scale_y_continuous(labels = scales::dollar) +
labs(title = "Lowest Product Categories Performers",
subtitle = "Data represents the total sales volume and value of least selling products.",
x = "Product Category",
y = "Total Sales Value",
size = "Quantity Sold",
color = "Per Unit Cost",
tag = "Fig.2")
cu <- demographics %>%
inner_join(coupon_redemptions, by = "household_id") %>%
filter(age == "19-24") %>%
select(coupon_upc, age, redemption_date, campaign_id) %>%
arrange(campaign_id)
View(cu)
Summer <- transactions %>%
inner_join(coupon_redemptions, by = "household_id") %>%
inner_join(demographics, by ="household_id") %>%
filter(campaign_id == "13", age == "19-24") %>%
select(household_id, age, quantity, product_id, sales_value) %>%
group_by(product_id, sales_value) %>%
summarise(product_amt = sum(quantity), total_sales = sum(sales_value))
## Warning in inner_join(., coupon_redemptions, by = "household_id"): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 3 of `x` matches multiple rows in `y`.
## ℹ Row 1549 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.
## `summarise()` has grouped output by 'product_id'. You can override using the
## `.groups` argument.
View(Summer)
#plot the prodcut sales in summer
ggplot(Summer, aes(x = sales_value, y = product_amt, color = total_sales)) +
geom_point(shape = 19, size = 2) +
labs(title = "Product Sales in Summer",
subtitle = "Best uses for coupons",
x = "Sales Value",
y = "Product Amount",
tag = "Fig.3")
# Coupon for top product
Top_Products <- products %>%
filter(product_id == "6534178")
Top_Products
## # A tibble: 1 × 7
## product_id manufacturer_id department brand product_category product_type
## <chr> <chr> <chr> <fct> <chr> <chr>
## 1 6534178 69 FUEL Private COUPON/MISC ITEMS GASOLINE-REG …
## # ℹ 1 more variable: package_size <chr>
Regork is one of the largest retailers in the world. I had the responsibility to analyze the 2017 data of 2469 households of frequent shoppers at Regork. Through my analysis I found very interesting information and anomalies. With the new information I found I had a few recommendations for them to utilize in hopes that it will increase this retailers profits.
With the data I found that ages 19-24 shop the least amount there. As well as spending the least amount of money as well so I felt that is a big market where Regork can make more revenue from. They purchase gasoline the most out of any other product at Regork so that can affect their prices as well.
Increase marketing especially within social media. This will bring more of the younger generation in because we use our phones a lot more than other age groups.
Could lower prices because the income for 19-24 isn’t as high as the other age groups. This will make them more likely to visit Regork.
Could offer coupons or discounts on gasoline. This will bring even more of the 19-24 age group to choose this stop over its competitors.
Could make a bundle where offering an in-store purchase will give you a discount on gasoline. This will make people a lot more likely to shop around and buy more product from Regork.