Introduction

Growth Strategy

Regork is in need of a strategy to expand their outreach in terms of sales. Getting a portion of the customer base to begin purchasing new kinds of products of which they have not yet purchased much, if any, would give Regork a new revenue stream they to discover and utilize. The company possesses an opportunity of growth by means of utilizing coupons to attract customers for whom the presence of coupons most highly motivates purchasing otherwise ignored products. The coupons can motivate these customers to introduce themselves to products they would not otherwise tend to purchase during these times. After the customers are introduced to these product categories, the intended outcome is for them to continue making purchases from these previously avoided areas now that they have had a discounted sample of them.

Method of Analysis

Age demographics for customers are evaluated for the largest difference in sales based on the presence or lack-there-of coupons. The age group for which coupons affect sales the most is then analyzed to find the correlated product category with the lowest sales for the demographic population. These coupons will be the most motivating method to get these highly susceptible customers to explore new categories during times when they otherwise would not.

Packages Required

library(completejourney)
library(dplyr)
library(tidyverse)
library(ggplot2)

(completejourney)

The data set that is used for analysis

(dplyr)

Grammar of data manipulation

(tidyverse)

System of packages used for data analysis

(ggplot2)

Allows for generation of data visualization

Data Preparation

Variables

transactions: The dataset containing relevant transaction information

demographics: The dataset of demographic groups of customers

coupons: The dataset of coupon information

age: The age groups of customers

sales_value: The dollar amount of corresponding transactions

total_sales: The sum of sales values

products: The dataset containing product information

product_category: Categories that contain related products

CPN_TS: Sales value of transactions that used coupons

CPN_EXC_TS: Sales value of transactions that did not use coupons

TS_COMPARE: Comparison between transactions using and not using coupons

CPN_45_PC: Sales value of products purchased heavily with coupons by 45-54 year olds

CPN_ENX_45_PC: Sales value of products purchased heavily without coupons by 45-54 year olds

T_45_PC: Total sales for age 45-54 year olds

BOT_10_CR_PC: Combined set of coupon sales for bottom 10 45-54 year old coupon users and total 45-54 year olds

BOT_10_COMPARE_EXC: Plot of the no-coupon sales of the 10 highest selling products without coupons

BOT_10_COMPARE2_CPN:Plot of the coupon-included sales of the 10 highest selling products without coupons

BOT_10_EXC_SUM: Plot of the no-coupon sales of the 10 highest selling products without coupons

BOT_10_CPN_SUM:Plot of the no-coupon sales of the 10 highest selling products without coupons

TOP_10_CR_PC: Combined set of coupon sales for top 10 45-54 year old coupon users and total 45-54 year olds

TOP_10_COMPARE1_EXC: Plot of the no-coupon sales of the 10 highest selling products with coupons

TOP_10_COMPARE2_CPN: Plot of the coupon-included sales of the 10 highest selling products with coupons

TOP_10_EXC_SUM: Table combining total and no-coupon sales of the 10 highest selling products with coupons

TOP_10_CPN_SUM: Table combining total and included coupon sales of the 10 highest selling products with coupons

Analysis

AGE RANGE ANALYSIS

TS_COMPARE <- ggplot() +
  geom_bar(data = CPN_TS, aes(x = age, y = total_sales / 1000), stat = "sum", alpha = .5, fill = "red", show.legend = F) +
  geom_bar(data = CPN_EXC_TS, aes(x = age, y = total_sales / 1000), stat = "sum", alpha = .5, fill = "blue", show.legend = F) +
  xlab("Age") + ylab("Total Sales by Thousand $")

The figure above displays a comparison between generated sales value for transactions that included coupons vs. transactions without the use of coupons. The columns separate these transactions by age group. It is evident that the age group 45-54 has the largest difference between sales with and without coupons. This implies that ages 45-54 are the most motivated to make purchases when offerred coupons.

PRODUCT CATEGORY ANALYSIS

BOT_10_COMPARE2_CPN <- ggplot() +
  geom_bar(data = BOT_10_CR_PC, aes(x = product_category, y = total_sales.y / 1000), stat = "sum", fill = "purple", show.legend = F) +
  xlab("Product Category") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  ylab("Total Sales by Thousand $")

BOT_10_COMPARE_EXC <- ggplot() +
  geom_bar(data = BOT_10_CR_PC, aes(x = product_category, y = total_sales / 1000), stat = "sum", fill = "orange", show.legend = F) +
  xlab("Product Category") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  ylab("Total Sales by Thousand $")

The figures above show the total sales value generated by the top 10 categories of products sold without using coupons when coupons are and are not present in the transactions. Demand for beer, baked bread, and deli meats appears to be significant.

COUPON v. NON-COUPON PURCHASES BY PRODUCT CATEGORY

TOP_10_COMPARE2CPN <- ggplot() +
  geom_bar(data = TOP_10_CR_PC, aes(x = product_category, y = total_sales.y / 1000), stat = "sum", fill = "purple", show.legend = F) +
  xlab("Product Category") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  ylab("Total Sales by Thousand $")

TOP_10_COMPARE1_EXC <- ggplot() +
  geom_bar(data = TOP_10_CR_PC, aes(x = product_category, y = total_sales / 1000), stat = "sum", fill = "orange", show.legend = F) +
  xlab("Product Category") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  ylab("Total Sales by Thousand $")

The figures above show the total sales value generated by the top 10 categories of products sold using coupons when coupons are and are not present in the transactions. The presence of coupons appear to yield significant changes for beef.

Summary

A key problem for Regork is the untapped potential for customers to diversify their purchasing habits. To find out the areas that could be diversified, the data can be broken down into customer age groups, coupon users, product categories, and corresponding sales. The age group for which the presence of coupons has the highest effect on purchasing patterns is that of 45-54 year olds. The product categories with the highest growth opportunity using coupons are beer/ales, baked bread/buns/rolls, and deli meats.

The recommended strategy for executing growth is to base a coupon campaign targeted at 45-54 year olds with offers on beer/ales, baked bread/buns/rolls, and deli meats.

A drawback of this conclusion may be that more data on motivation for existing offered coupon strategies is required. Profit margins on products is not factored into this conclusion-only sales revenue. Company profit is founded upon product profit margins, and coupon discounts may reduce this. Based on sales value alone, however, this new strategy is sound.