As data scientists for the national grocery chain Regork we have been tasked with identifying a potential area of growth where the company can invest future resources to increase revenue and profits.
As will become clear in our exploration of the The Complete Journey data set throughout this report, there is a consistent pattern of decreased sales after major holidays throughout the year. Although this drop in sales is not unexpected considering the natural purchasing habits of customers leading up to a holiday, it raises an important question and exposes a potential growth opportunity for Regork:
How do we get customers back in stores faster following a major holiday?
Extensive analysis of Regork’s historical data will expose potential growth opportunities in this area.
To address this problem, we started by validating our assumptions to solidify addressing the drop in sales immediately following a holiday were both founded and worth investing time in. To complete this validation, we explored the Transactions data over time to understand the lowest occurrences of sales.
Once validated, we moved to analyzing the relationship between transactions and Campaigns throughout the year to determine what kind of campaigns were occurring and what type of value they were bringing. This, tied in with Campaign Descriptions, provided insight to the relationships between holidays and campaign events.
Using the Transactions, Products, Coupons, Campaign Descriptions, and Demographics data sets, we explored the relationship between these components to understand what products were selling the most and how that information was impacted by demographics.
For a more focused approach, our initial analysis led us to focus in on the busiest times of the year, Q4, for deeper analysis of how changes in campaign approach could help bring customers back into stores faster following a major holiday.
We have determined through detailed analysis of the data available in The Complete Journey data set that Regork can capitalize on an opportunity for growth by:
Implementing a new targeted campaign type directly following the conclusion of a major holiday.
Although today there is a solid distribution of campaign types throughout the year that target both individual customer needs and event driven scenarios such as holidays, there is an opportunity to introduce a new campaign type that targets the most purchased products during the lowest sales days following a major holiday.
The following packages are required to execute the code in this project:
library(completejourney) # Grocery store transaction data from a group of 2,469 households
library(ggplot2) # A system for 'declaratively' creating graphics, based on "The Grammar of Graphics"
library(tidyverse) # Makes it easy to install and load multiple 'tidyverse' packages in a single step
library(lubridate) # Provides tools that make it easier to parse and manipulate dates
library(scales) # Map data to aesthetics
library(kableExtra) # This is a very simple table generator
library(gt) # This is a helpful tables formatting package
library(gtExtras) # Additional functions for creating beautiful tables with 'gt'
library(grid) # Adds an nx by ny rectangular grid to an existing plot
library(gridExtra) # Provides a number of user-level functions to work with "grid" graphics
library(wesanderson) # Fun color palettes based on Wes Anderson
The Complete Journey data set was used to complete this analysis. This provides access to data sets characterizing household level transactions over one year from a group of 2,469 households who are frequent shoppers at a grocery store.
Below outlines the Complete Journey data sets used for this report:
# get transactions data
transactions <- get_transactions()
transactions
## # A tibble: 1,469,307 × 11
## household_id store_id basket_id product_id quantity sales_value retail_disc
## <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 900 330 31198570044 1095275 1 0.5 0
## 2 900 330 31198570047 9878513 1 0.99 0.1
## 3 1228 406 31198655051 1041453 1 1.43 0.15
## 4 906 319 31198705046 1020156 1 1.5 0.29
## 5 906 319 31198705046 1053875 2 2.78 0.8
## 6 906 319 31198705046 1060312 1 5.49 0.5
## 7 906 319 31198705046 1075313 1 1.5 0.29
## 8 1058 381 31198676055 985893 1 1.88 0.21
## 9 1058 381 31198676055 988791 1 1.5 1.29
## 10 1058 381 31198676055 9297106 1 2.69 0
## # ℹ 1,469,297 more rows
## # ℹ 4 more variables: coupon_disc <dbl>, coupon_match_disc <dbl>, week <int>,
## # transaction_timestamp <dttm>
# get campaigns data
campaigns
## # A tibble: 6,589 × 2
## campaign_id household_id
## <chr> <chr>
## 1 1 105
## 2 1 1238
## 3 1 1258
## 4 1 1483
## 5 1 2200
## 6 1 293
## 7 1 529
## 8 1 536
## 9 1 568
## 10 1 630
## # ℹ 6,579 more rows
# get campaign description data
campaign_descriptions
## # A tibble: 27 × 4
## campaign_id campaign_type start_date end_date
## <chr> <ord> <date> <date>
## 1 1 Type B 2017-03-03 2017-04-09
## 2 2 Type B 2017-03-08 2017-04-09
## 3 3 Type C 2017-03-13 2017-05-08
## 4 4 Type B 2017-03-29 2017-04-30
## 5 5 Type B 2017-04-03 2017-05-07
## 6 6 Type C 2017-04-19 2017-05-21
## 7 7 Type B 2017-04-24 2017-05-28
## 8 8 Type A 2017-05-08 2017-06-25
## 9 9 Type B 2017-05-31 2017-07-02
## 10 10 Type B 2017-06-28 2017-07-30
## # ℹ 17 more rows
# get demographics data
demographics
## # A tibble: 801 × 8
## household_id age income home_ownership marital_status household_size
## <chr> <ord> <ord> <ord> <ord> <ord>
## 1 1 65+ 35-49K Homeowner Married 2
## 2 1001 45-54 50-74K Homeowner Unmarried 1
## 3 1003 35-44 25-34K <NA> Unmarried 1
## 4 1004 25-34 15-24K <NA> Unmarried 1
## 5 101 45-54 Under 15K Homeowner Married 4
## 6 1012 35-44 35-49K <NA> Married 5+
## 7 1014 45-54 15-24K <NA> Married 4
## 8 1015 45-54 50-74K Homeowner Unmarried 1
## 9 1018 45-54 35-49K Homeowner Married 5+
## 10 1020 45-54 25-34K Homeowner Married 2
## # ℹ 791 more rows
## # ℹ 2 more variables: household_comp <ord>, kids_count <ord>
# get coupon redemption data
coupon_redemptions
## # A tibble: 2,102 × 4
## household_id coupon_upc campaign_id redemption_date
## <chr> <chr> <chr> <date>
## 1 1029 51380041013 26 2017-01-01
## 2 1029 51380041313 26 2017-01-01
## 3 165 53377610033 26 2017-01-03
## 4 712 51380041013 26 2017-01-07
## 5 712 54300016033 26 2017-01-07
## 6 2488 51200092776 26 2017-01-10
## 7 2488 51410010050 26 2017-01-10
## 8 1923 53000012033 26 2017-01-14
## 9 1923 54300021057 26 2017-01-14
## 10 1923 57047091041 26 2017-01-14
## # ℹ 2,092 more rows
# get product data
products
## # A tibble: 92,331 × 7
## product_id manufacturer_id department brand product_category product_type
## <chr> <chr> <chr> <fct> <chr> <chr>
## 1 25671 2 GROCERY Natio… FRZN ICE ICE - CRUSH…
## 2 26081 2 MISCELLANEOUS Natio… <NA> <NA>
## 3 26093 69 PASTRY Priva… BREAD BREAD:ITALI…
## 4 26190 69 GROCERY Priva… FRUIT - SHELF S… APPLE SAUCE
## 5 26355 69 GROCERY Priva… COOKIES/CONES SPECIALTY C…
## 6 26426 69 GROCERY Priva… SPICES & EXTRAC… SPICES & SE…
## 7 26540 69 GROCERY Priva… COOKIES/CONES TRAY PACK/C…
## 8 26601 69 DRUG GM Priva… VITAMINS VITAMIN - M…
## 9 26636 69 PASTRY Priva… BREAKFAST SWEETS SW GDS: SW …
## 10 26691 16 GROCERY Priva… PNT BTR/JELLY/J… HONEY
## # ℹ 92,321 more rows
## # ℹ 1 more variable: package_size <chr>
Below outlines the data frames created using the Complete Journey data sets for this report:
# total sales transactions by day
trans_by_day <- transactions %>%
mutate(transaction_timestamp = ymd_hms(transaction_timestamp),
transaction_timestamp = as_date(transaction_timestamp)) %>%
group_by(transaction_timestamp) %>%
summarize(daily_total_sales = sum(sales_value))
trans_by_day
## # A tibble: 364 × 2
## transaction_timestamp daily_total_sales
## <date> <dbl>
## 1 2017-01-01 10477.
## 2 2017-01-02 12775.
## 3 2017-01-03 13311.
## 4 2017-01-04 12194.
## 5 2017-01-05 12273.
## 6 2017-01-06 12313.
## 7 2017-01-07 14566.
## 8 2017-01-08 15939.
## 9 2017-01-09 12709.
## 10 2017-01-10 8885.
## # ℹ 354 more rows
# holidays for 2017
holidays <- ymd(c("2017-01-01", "2017-02-05", "2017-02-14", "2017-03-17",
"2017-04-16", "2017-05-05", "2017-05-14", "2017-05-29",
"2017-06-18", "2017-07-04", "2017-09-04", "2017-10-31",
"2017-11-23", "2017-12-25"))
holidays
## [1] "2017-01-01" "2017-02-05" "2017-02-14" "2017-03-17" "2017-04-16"
## [6] "2017-05-05" "2017-05-14" "2017-05-29" "2017-06-18" "2017-07-04"
## [11] "2017-09-04" "2017-10-31" "2017-11-23" "2017-12-25"
# holidays grouped by quarter
# New Years, Super Bowl, Valentine's Day, St. Patrick's Day
q1_holiday_date <- ymd(c("2017-01-01", "2017-02-05", "2017-02-14", "2017-03-17"))
# Easter Sunday, Cinco de Mayo, Mother's Day, Memorial Day
q2_holiday_date <- ymd(c("2017-04-16", "2017-05-05", "2017-05-14",
"2017-05-29"))
# Father's Day, Independence Day, Labor Day
q3_holiday_date <- ymd(c("2017-06-18", "2017-07-04", "2017-09-04"))
# Halloween, Thanksgiving Day, Christmas Day
q4_holiday_date <- ymd(c("2017-10-31", "2017-11-23", "2017-12-25"))
q1_holiday_date
## [1] "2017-01-01" "2017-02-05" "2017-02-14" "2017-03-17"
q2_holiday_date
## [1] "2017-04-16" "2017-05-05" "2017-05-14" "2017-05-29"
q3_holiday_date
## [1] "2017-06-18" "2017-07-04" "2017-09-04"
q4_holiday_date
## [1] "2017-10-31" "2017-11-23" "2017-12-25"
# Top 25 sales days in 2017
top_sales_days <- transactions %>%
mutate(transaction_timestamp = ymd_hms(transaction_timestamp),
transaction_timestamp = as_date(transaction_timestamp)) %>%
group_by(transaction_timestamp) %>%
summarize(daily_total_sales = sum(sales_value)) %>%
slice_max(daily_total_sales, n = 25)
top_sales_days
## # A tibble: 25 × 2
## transaction_timestamp daily_total_sales
## <date> <dbl>
## 1 2017-12-23 24760.
## 2 2017-11-22 20145.
## 3 2017-12-03 19612.
## 4 2017-12-22 19095.
## 5 2017-11-05 18949.
## 6 2017-02-04 18881.
## 7 2017-12-30 17882.
## 8 2017-04-15 17780.
## 9 2017-11-04 17723.
## 10 2017-08-06 17580.
## # ℹ 15 more rows
# Bottom 25 sales days in 2017
bottom_sales_days <- transactions %>%
mutate(transaction_timestamp = ymd_hms(transaction_timestamp),
transaction_timestamp = as_date(transaction_timestamp)) %>%
group_by(transaction_timestamp) %>%
summarize(daily_total_sales = sum(sales_value)) %>%
slice_min(daily_total_sales, n = 25)
bottom_sales_days
## # A tibble: 25 × 2
## transaction_timestamp daily_total_sales
## <date> <dbl>
## 1 2017-11-23 6963.
## 2 2017-04-11 8515.
## 3 2017-03-21 8556.
## 4 2017-07-19 8735.
## 5 2017-01-18 8808.
## 6 2017-10-19 8829.
## 7 2017-01-10 8885.
## 8 2017-11-24 8997.
## 9 2017-02-23 9123.
## 10 2017-06-22 9132.
## # ℹ 15 more rows
# Number of campaigns by quarter
camp_typ_qtr <- campaigns %>%
inner_join(campaign_descriptions, by = "campaign_id") %>%
mutate(camp_qtr = case_when(
start_date >= "2017-01-01" & start_date <= "2017-03-31" ~ "Q1",
start_date >= "2017-04-01" & start_date <= "2017-06-30" ~ "Q2",
start_date >= "2017-07-01" & start_date <= "2017-09-30" ~ "Q3",
start_date >= "2017-10-01" & start_date <= "2017-12-31" ~ "Q4",
TRUE ~ "N/A"
)) %>%
filter(camp_qtr != "N/A") %>% # remove dates outside of specified quarters
group_by(campaign_type, camp_qtr) %>%
summarize(campaign_count = n()) %>%
arrange(camp_qtr)
camp_typ_qtr
## # A tibble: 12 × 3
## # Groups: campaign_type [3]
## campaign_type camp_qtr campaign_count
## <ord> <chr> <int>
## 1 Type A Q1 361
## 2 Type B Q1 142
## 3 Type C Q1 12
## 4 Type A Q2 1076
## 5 Type B Q2 663
## 6 Type C Q2 65
## 7 Type A Q3 1077
## 8 Type B Q3 384
## 9 Type C Q3 241
## 10 Type A Q4 1133
## 11 Type B Q4 1044
## 12 Type C Q4 244
# Number of campaigns by week for Q4 (campaign start)
camp_typ_week <- campaigns %>%
inner_join(campaign_descriptions, by = "campaign_id") %>%
filter(start_date >= "2017-10-01") %>%
mutate(week_of_year = isoweek(start_date)) %>%
group_by(campaign_type, week_of_year) %>%
summarize(campaign_count = n()) %>%
arrange(week_of_year)
camp_typ_week
## # A tibble: 7 × 3
## # Groups: campaign_type [3]
## campaign_type week_of_year campaign_count
## <ord> <dbl> <int>
## 1 Type B 40 188
## 2 Type B 42 202
## 3 Type A 44 1133
## 4 Type B 46 130
## 5 Type C 48 244
## 6 Type B 49 341
## 7 Type B 52 183
# Total sales each week by campaign type
weekly_campaign_sales <- transactions %>%
mutate(transaction_timestamp = ymd_hms(transaction_timestamp),
transaction_timestamp = as_date(transaction_timestamp)) %>%
filter(coupon_disc > 0 | retail_disc > 0 | coupon_match_disc > 0) %>%
filter(week > 1) %>% #removing outliers
inner_join(campaigns, by = "household_id") %>%
inner_join(campaign_descriptions, by = "campaign_id") %>%
group_by(campaign_type, week) %>%
summarize(total_sales = sum(sales_value))
weekly_campaign_sales
## # A tibble: 156 × 3
## # Groups: campaign_type [3]
## campaign_type week total_sales
## <ord> <int> <dbl>
## 1 Type A 2 111130.
## 2 Type A 3 102626.
## 3 Type A 4 103600.
## 4 Type A 5 101706.
## 5 Type A 6 107574.
## 6 Type A 7 103955.
## 7 Type A 8 91009.
## 8 Type A 9 107696.
## 9 Type A 10 113033.
## 10 Type A 11 114503.
## # ℹ 146 more rows
# Total sales each week for Q4 by campaign type
weekly_campaign_sales_q4 <- transactions %>%
mutate(transaction_timestamp = ymd_hms(transaction_timestamp),
transaction_timestamp = as_date(transaction_timestamp)) %>%
filter(coupon_disc > 0 | retail_disc > 0 | coupon_match_disc > 0) %>%
filter(week >= 40) %>%
inner_join(campaigns, by = "household_id") %>%
inner_join(campaign_descriptions, by = "campaign_id") %>%
group_by(campaign_type, week) %>%
summarize(total_sales = sum(sales_value))
weekly_campaign_sales_q4
## # A tibble: 42 × 3
## # Groups: campaign_type [3]
## campaign_type week total_sales
## <ord> <int> <dbl>
## 1 Type A 40 96477.
## 2 Type A 41 101620.
## 3 Type A 42 101292.
## 4 Type A 43 99382.
## 5 Type A 44 98932.
## 6 Type A 45 119821.
## 7 Type A 46 104640.
## 8 Type A 47 110437.
## 9 Type A 48 109563.
## 10 Type A 49 108985.
## # ℹ 32 more rows
# products by campaign type
product_campaign <- products %>%
inner_join(coupons, by = "product_id") %>%
inner_join(campaign_descriptions, by = "campaign_id") %>%
group_by(campaign_type, product_category) %>%
summarize(count = n())
product_campaign
## # A tibble: 403 × 3
## # Groups: campaign_type [3]
## campaign_type product_category count
## <ord> <chr> <int>
## 1 Type A ADULT INCONTINENCE 150
## 2 Type A AIR CARE 86
## 3 Type A ANALGESICS 1023
## 4 Type A ANTACIDS 545
## 5 Type A APPAREL 6
## 6 Type A APPLES 468
## 7 Type A AUDIO/VIDEO PRODUCTS 4
## 8 Type A AUTOMOTIVE PRODUCTS 4
## 9 Type A BABY FOODS 1366
## 10 Type A BABY HBC 697
## # ℹ 393 more rows
# Lowest sales dates following a holiday (within 10 days)
bottom_dates <- c("2017-03-21", "2017-01-10", "2017-11-24", "2017-02-23",
"2017-06-22", "2017-03-23", "2017-03-22", "2017-11-30")
bottom_dates
## [1] "2017-03-21" "2017-01-10" "2017-11-24" "2017-02-23" "2017-06-22"
## [6] "2017-03-23" "2017-03-22" "2017-11-30"
# Top products sold on lowest sales days (post holiday)
top_prod_lowest_days <- transactions %>%
inner_join(products, by = "product_id") %>%
mutate(transaction_timestamp = ymd_hms(transaction_timestamp),
transaction_timestamp = as_date(transaction_timestamp)) %>%
filter(transaction_timestamp %in% bottom_dates) %>%
group_by(transaction_timestamp, product_category) %>%
summarize(sales_count = n()) %>%
slice_max(sales_count, n = 10) %>%
arrange(transaction_timestamp, desc(sales_count))
top_prod_lowest_days
## # A tibble: 83 × 3
## # Groups: transaction_timestamp [8]
## transaction_timestamp product_category sales_count
## <date> <chr> <int>
## 1 2017-01-10 SOFT DRINKS 133
## 2 2017-01-10 FLUID MILK PRODUCTS 98
## 3 2017-01-10 BAKED BREAD/BUNS/ROLLS 85
## 4 2017-01-10 CHEESE 83
## 5 2017-01-10 FRZN MEAT/MEAT DINNERS 81
## 6 2017-01-10 SOUP 75
## 7 2017-01-10 YOGURT 69
## 8 2017-01-10 BAG SNACKS 65
## 9 2017-01-10 BEEF 60
## 10 2017-01-10 COLD CEREAL 58
## # ℹ 73 more rows
# The most common products purchased after a holiday
total_top_prods <- top_prod_lowest_days %>%
group_by(product_category) %>%
summarize(product_occurance = sum(sales_count)) %>%
slice_max(product_occurance, n = 10) %>%
arrange(desc(product_occurance))
total_top_prods
## # A tibble: 10 × 2
## product_category product_occurance
## <chr> <int>
## 1 SOFT DRINKS 1029
## 2 FLUID MILK PRODUCTS 875
## 3 BAKED BREAD/BUNS/ROLLS 733
## 4 CHEESE 649
## 5 BAG SNACKS 590
## 6 SOUP 418
## 7 FRZN MEAT/MEAT DINNERS 417
## 8 CANDY - CHECKLANE 355
## 9 BEEF 341
## 10 YOGURT 241
# top product categories for Type A campaigns
camp_a_top_prod <- products %>%
inner_join(coupons, by = "product_id") %>%
inner_join(campaign_descriptions, by = "campaign_id") %>%
filter(campaign_type == "Type A") %>%
group_by(product_category) %>%
summarize(product_occurance = n()) %>%
slice_max(product_occurance, n = 10) %>%
arrange(desc(product_occurance))
camp_a_top_prod
## # A tibble: 10 × 2
## product_category product_occurance
## <chr> <int>
## 1 MAKEUP AND TREATMENT 4807
## 2 FRZN MEAT/MEAT DINNERS 4208
## 3 HAIR CARE PRODUCTS 3831
## 4 BEEF 3314
## 5 FROZEN PIZZA 2996
## 6 ICE CREAM/MILK/SHERBTS 2637
## 7 CHEESE 2428
## 8 LUNCHMEAT 2425
## 9 YOGURT 2234
## 10 ORAL HYGIENE PRODUCTS 2226
# top product categories for Type B campaigns
camp_b_top_prod <- products %>%
inner_join(coupons, by = "product_id") %>%
inner_join(campaign_descriptions, by = "campaign_id") %>%
filter(campaign_type == "Type B") %>%
group_by(product_category) %>%
summarize(product_occurance = n()) %>%
slice_max(product_occurance, n = 10) %>%
arrange(desc(product_occurance))
camp_b_top_prod
## # A tibble: 10 × 2
## product_category product_occurance
## <chr> <int>
## 1 GREETING CARDS/WRAP/PARTY SPLY 1343
## 2 MAKEUP AND TREATMENT 777
## 3 BABY FOODS 672
## 4 FRZN MEAT/MEAT DINNERS 586
## 5 CHEESE 532
## 6 COLD CEREAL 407
## 7 REFRGRATD JUICES/DRNKS 381
## 8 FROZEN PIZZA 351
## 9 DIAPERS & DISPOSABLES 266
## 10 REFRGRATD DOUGH PRODUCTS 249
# top product categories for Type C campaigns
camp_c_top_prod <- products %>%
inner_join(coupons, by = "product_id") %>%
inner_join(campaign_descriptions, by = "campaign_id") %>%
filter(campaign_type == "Type C") %>%
group_by(product_category) %>%
summarize(product_occurance = n()) %>%
slice_max(product_occurance, n = 10) %>%
arrange(desc(product_occurance))
camp_c_top_prod
## # A tibble: 10 × 2
## product_category product_occurance
## <chr> <int>
## 1 HAIR CARE PRODUCTS 2155
## 2 DRY BN/VEG/POTATO/RICE 792
## 3 SOAP - LIQUID & BAR 665
## 4 PASTA SAUCE 637
## 5 DEODORANTS 534
## 6 SALD DRSNG/SNDWCH SPRD 526
## 7 LAUNDRY DETERGENTS 433
## 8 TEAS 337
## 9 LAUNDRY ADDITIVES 304
## 10 HAND/BODY/FACIAL PRODUCTS 197
# Daily sales count for top products sold on low sales day (post holiday)
avg_low_count <- transactions %>%
inner_join(products, by = "product_id") %>%
filter(product_category %in% c("BAG SNACKS", "BAKED BREAD/BUNS/ROLLS",
"FLUID MILK PRODUCTS", "SOFT DRINKS", "SOUP",
"CANDY - CHECKLANE")) %>%
group_by(week, product_category) %>%
summarize(purchase_count = n())
avg_low_count
## # A tibble: 318 × 3
## # Groups: week [53]
## week product_category purchase_count
## <int> <chr> <int>
## 1 1 BAG SNACKS 102
## 2 1 BAKED BREAD/BUNS/ROLLS 105
## 3 1 CANDY - CHECKLANE 48
## 4 1 FLUID MILK PRODUCTS 103
## 5 1 SOFT DRINKS 231
## 6 1 SOUP 96
## 7 2 BAG SNACKS 860
## 8 2 BAKED BREAD/BUNS/ROLLS 930
## 9 2 CANDY - CHECKLANE 404
## 10 2 FLUID MILK PRODUCTS 1086
## # ℹ 308 more rows
# Household type for product categories
house_comp_purchase <- transactions %>%
inner_join(demographics, by = "household_id") %>%
inner_join(products, by = "product_id") %>%
filter(product_category %in% c("BAG SNACKS", "BAKED BREAD/BUNS/ROLLS",
"FLUID MILK PRODUCTS", "SOFT DRINKS", "SOUP",
"CANDY - CHECKLANE")) %>%
group_by(household_comp, product_category) %>%
summarize(purchase_count = n())
house_comp_purchase
## # A tibble: 24 × 3
## # Groups: household_comp [4]
## household_comp product_category purchase_count
## <ord> <chr> <int>
## 1 1 Adult Kids BAG SNACKS 2306
## 2 1 Adult Kids BAKED BREAD/BUNS/ROLLS 3200
## 3 1 Adult Kids CANDY - CHECKLANE 1044
## 4 1 Adult Kids FLUID MILK PRODUCTS 3177
## 5 1 Adult Kids SOFT DRINKS 4560
## 6 1 Adult Kids SOUP 1367
## 7 1 Adult No Kids BAG SNACKS 5830
## 8 1 Adult No Kids BAKED BREAD/BUNS/ROLLS 7572
## 9 1 Adult No Kids CANDY - CHECKLANE 3251
## 10 1 Adult No Kids FLUID MILK PRODUCTS 8049
## # ℹ 14 more rows
# Household income for product categories
house_income_purchase <- transactions %>%
inner_join(demographics, by = "household_id") %>%
inner_join(products, by = "product_id") %>%
filter(product_category %in% c("BAG SNACKS", "BAKED BREAD/BUNS/ROLLS",
"FLUID MILK PRODUCTS", "SOFT DRINKS", "SOUP",
"CANDY - CHECKLANE")) %>%
mutate(income = fct_lump(income, n = 8)) %>% # Condensing income groups
group_by(income, product_category) %>%
summarize(purchase_count = n())
house_income_purchase
## # A tibble: 54 × 3
## # Groups: income [9]
## income product_category purchase_count
## <ord> <chr> <int>
## 1 Under 15K BAG SNACKS 1803
## 2 Under 15K BAKED BREAD/BUNS/ROLLS 2104
## 3 Under 15K CANDY - CHECKLANE 925
## 4 Under 15K FLUID MILK PRODUCTS 1890
## 5 Under 15K SOFT DRINKS 3606
## 6 Under 15K SOUP 1073
## 7 15-24K BAG SNACKS 1809
## 8 15-24K BAKED BREAD/BUNS/ROLLS 2008
## 9 15-24K CANDY - CHECKLANE 1015
## 10 15-24K FLUID MILK PRODUCTS 2035
## # ℹ 44 more rows
Transactions over Time by Quarter
Our analysis began with the validation of our assumptions that there is a decrease in sales following a major holiday. To do this, we started by analyzing sales trends over time by quarter while indicating major holidays on the line graphs to visualize decreases in relation to major holidays.
The below line graph outlines transaction activity over time for each quarter. The vertical lines highlighted in yellow represent major holidays throughout the year.
# Graph of Q1 transactions by day
q1_day <- trans_by_day %>%
filter(transaction_timestamp <= "2017-03-31") %>%
ggplot(aes(x = transaction_timestamp, y = daily_total_sales)) +
geom_line(size = .5) +
geom_vline(xintercept = q1_holiday_date, color = "#D67236") +
scale_color_manual(values = "#5B1A18") +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
scale_y_continuous(labels = scales::dollar) +
labs(title = "Q1 Total Daily Sales",
x = "Total Sales",
y = "Time (days)") +
geom_text(aes(x = as.Date("2017-01-01"), label = "\n New Years", y = 9, angle = 090,
color = "#FD6467"), nudge_y = 17500, show.legend = FALSE, size = 3) +
geom_text(aes(x = as.Date("2017-02-05"), label = "\n Super Bowl", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 17500, show.legend = FALSE, size = 3) +
geom_text(aes(x = as.Date("2017-02-14"), label = "\n Valentine's Day", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 17000, show.legend = FALSE, size = 3) +
geom_text(aes(x = as.Date("2017-03-17"), label = "\n St. Patty's Day", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 17300, show.legend = FALSE, size = 2.5)
# Graph of Q2 transactions by day
q2_day <- trans_by_day %>%
filter(transaction_timestamp <= "2017-06-30"
& transaction_timestamp > "2017-03-31") %>%
ggplot(aes(x = transaction_timestamp, y = daily_total_sales)) +
geom_line(size = .5) +
geom_vline(xintercept = q2_holiday_date, color = "#D67236") +
scale_color_manual(values = "#5B1A18") +
scale_y_continuous(labels = scales::dollar) +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Q2 Total Daily Sales",
x = "Total Sales",
y = "Time (days)") +
geom_text(aes(x = as.Date("2017-04-16"), label = "\n Easter Sunday", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 16000, show.legend = FALSE, size = 3) +
geom_text(aes(x = as.Date("2017-05-05"), label = "\n Cinco de Mayo", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 10000, show.legend = FALSE, size = 2.5) +
geom_text(aes(x = as.Date("2017-05-14"), label = "\n Mother's Day", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 16500, show.legend = FALSE, size = 3) +
geom_text(aes(x = as.Date("2017-05-29"), label = "\n Memorial Day", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 16400, show.legend = FALSE, size = 2.5)
# Graph of Q3 transactions by day
q3_day <- trans_by_day %>%
filter(transaction_timestamp <= "2017-09-30"
& transaction_timestamp > "2017-06-30") %>%
ggplot(aes(x = transaction_timestamp, y = daily_total_sales)) +
geom_line(size = .5) +
geom_vline(xintercept = q3_holiday_date, color = "#D67236") +
scale_color_manual(values = "#5B1A18") +
scale_y_continuous(labels = scales::dollar) +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Q3 Total Daily Sales",
x = "Total Sales",
y = "Time (days)") +
geom_text(aes(x = as.Date("2017-06-18"), label = "\n Father's Day", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 16300, show.legend = FALSE, size = 3) +
geom_text(aes(x = as.Date("2017-07-04"), label = "\n 4th of July", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 16600, show.legend = FALSE, size = 2.5) +
geom_text(aes(x = as.Date("2017-09-04"), label = "\n Labor Day", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 16500, show.legend = FALSE, size = 3)
# Graph of Q4 transactions by day
q4_day <- trans_by_day %>%
filter(transaction_timestamp <= "2017-12-31"
& transaction_timestamp > "2017-09-30") %>%
ggplot(aes(x = transaction_timestamp, y = daily_total_sales)) +
geom_line(size = .5) +
geom_vline(xintercept = q4_holiday_date, color = "#D67236") +
scale_color_manual(values = "#5B1A18") +
scale_y_continuous(labels = scales::dollar) +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Q4 Total Daily Sales",
x = "Total Sales",
y = "Time (days)") +
geom_text(aes(x = as.Date("2017-10-31"), label = "\n Halloween", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 22500, show.legend = FALSE, size = 3) +
geom_text(aes(x = as.Date("2017-11-23"), label = "\n Thanksgiving", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 22000, show.legend = FALSE, size = 3) +
geom_text(aes(x = as.Date("2017-12-25"), label = "\n Christmas", y = 9, angle = 90,
color = "#FD6467"), nudge_y = 22500, show.legend = FALSE, size = 3)
gridExtra::grid.arrange(q1_day, q2_day, q3_day, q4_day, ncol = 2)
Top 25 and Bottom 25 Transaction Days
Once validated, we solidified the value in pursuing this opportunity by looking at the top 25 sales days and the bottom 25 sales days for the data provided. As highlighted below, for the lowest transaction days there are 8 that fall within 10 days following a given holiday. Additionally, we see a correlate between tops sales days and holidays (as expected).
Based on the information determined here, we decided to focus in on Q4 to narrow the scope of our exploration.
# Create a table for the top 25
top_sales_table <- top_sales_days %>%
as.data.frame() %>%
select(transaction_timestamp, daily_total_sales) %>%
arrange(daily_total_sales) %>%
gt() %>%
gt_highlight_rows(rows = grepl("2017-12-30|2017-12-22|2017-11-22|2017-12-23|2017-04-15|2017-02-05|2017-02-12|2017-03-12|2017-04-15|2017-05-21|2017-06-11|2017-07-04|2017-07-01|2017-10-22|2017-11-21|2017-12-31", transaction_timestamp),
fill = "#F1BB7B") %>%
tab_style(style = cell_fill(color = "#D67236"), locations = cells_column_labels()) %>%
opt_stylize(style = 5) %>%
fmt_date(columns = 'transaction_timestamp') %>%
fmt_currency(columns = 'daily_total_sales') %>%
cols_label(transaction_timestamp = "Date",
daily_total_sales = "Total Sales") %>%
cols_align(align = "left") %>%
tab_header("Top 25 Total Sales Days",
subtitle = html("Top sales days leading up to and including a holiday <br> are highlighted in yellow (within 10 days)")) %>%
tab_options(heading.background.color = "#5B1A18") %>%
opt_horizontal_padding(scale = 3)
# Create a table for the bottom 25
bottom_sales_table <- bottom_sales_days %>%
as.data.frame() %>%
select(transaction_timestamp, daily_total_sales) %>%
gt() %>%
gt_highlight_rows(rows = grepl("2017-01-10|2017-02-23|2017-03-21|2017-03-22|2017-03-23|2017-06-22|2017-11-24|2017-11-30", transaction_timestamp),
fill = "#F1BB7B") %>%
tab_style(style = cell_fill(color = "#D67236"), locations = cells_column_labels()) %>%
opt_stylize(style = 5) %>%
fmt_date(columns = 'transaction_timestamp') %>%
fmt_currency(columns = 'daily_total_sales') %>%
cols_label(transaction_timestamp = "Date",
daily_total_sales = "Total Sales") %>%
cols_align(align = "left") %>%
tab_header("Bottom 25 Total Sales Days",
subtitle = html("Bottom sales days following a holiday are highlighted <br> in yellow (within 10 days)")) %>%
tab_options(heading.background.color = "#5B1A18") %>%
opt_horizontal_padding(scale = 3)
gt_two_column_layout(list(top_sales_table, bottom_sales_table))
| Top 25 Total Sales Days | |
| Top sales days leading up to and including a holiday are highlighted in yellow (within 10 days) |
|
| Date | Total Sales |
|---|---|
| 2017-06-11 | $16,410.19 |
| 2017-12-16 | $16,449.13 |
| 2017-04-02 | $16,482.90 |
| 2017-12-31 | $16,574.57 |
| 2017-05-21 | $16,783.00 |
| 2017-07-04 | $16,868.78 |
| 2017-06-04 | $16,873.89 |
| 2017-10-01 | $16,906.69 |
| 2017-10-22 | $16,915.08 |
| 2017-02-05 | $16,997.21 |
| 2017-02-12 | $17,013.48 |
| 2017-03-12 | $17,021.89 |
| 2017-07-01 | $17,068.73 |
| 2017-05-07 | $17,098.94 |
| 2017-11-21 | $17,403.48 |
| 2017-08-06 | $17,580.16 |
| 2017-11-04 | $17,722.95 |
| 2017-04-15 | $17,779.79 |
| 2017-12-30 | $17,882.26 |
| 2017-02-04 | $18,881.38 |
| 2017-11-05 | $18,949.29 |
| 2017-12-22 | $19,095.37 |
| 2017-12-03 | $19,612.10 |
| 2017-11-22 | $20,144.70 |
| 2017-12-23 | $24,760.10 |
| Bottom 25 Total Sales Days | |
| Bottom sales days following a holiday are highlighted in yellow (within 10 days) |
|
| Date | Total Sales |
|---|---|
| 2017-11-23 | $6,962.69 |
| 2017-04-11 | $8,515.04 |
| 2017-03-21 | $8,555.63 |
| 2017-07-19 | $8,734.51 |
| 2017-01-18 | $8,807.68 |
| 2017-10-19 | $8,829.11 |
| 2017-01-10 | $8,885.30 |
| 2017-11-24 | $8,996.58 |
| 2017-02-23 | $9,123.08 |
| 2017-06-22 | $9,131.61 |
| 2017-03-23 | $9,206.23 |
| 2017-09-26 | $9,251.59 |
| 2017-01-27 | $9,264.53 |
| 2017-03-07 | $9,281.16 |
| 2017-01-19 | $9,311.91 |
| 2017-03-22 | $9,340.74 |
| 2017-05-25 | $9,379.18 |
| 2017-04-06 | $9,420.08 |
| 2017-08-30 | $9,439.23 |
| 2017-12-13 | $9,486.49 |
| 2017-09-21 | $9,491.98 |
| 2017-11-30 | $9,499.69 |
| 2017-07-26 | $9,504.61 |
| 2017-01-17 | $9,516.80 |
| 2017-01-26 | $9,581.30 |
Campaign Types Over Time
With our focused data set, we next evaluated the relationship of promotions and how the type and frequency related to the dips in sales we observed. To understand the following graphs, it is important to note the differences between campaign types.
Type A: Customers participating in this type of
campaign received 16 coupons based on the customer’s prior purchase
behavior.
Type B & C: Customers participating in this type of
campaign received all coupons pertaining to that campaign.
Per the data sets provided, there is no given distinction between Type B & C campaigns.
The important distinction between Type A and Type B and C campaigns is that Type A campaigns target customers based on their purchasing habits where Type B and C target customers based on the type of campaign being run.
# Bar graph of campaign count by quarter by type
camp_typ_qtr_graph <- camp_typ_qtr %>%
ggplot(aes(x = camp_qtr, y = campaign_count, fill = campaign_type)) +
geom_bar(position = "dodge", stat = "identity") +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Campaign Count by Quarter", x = "Quarter",
y = "Campaign Count", fill = "Campaign Type") +
scale_fill_manual(values = wes_palette("GrandBudapest1", n = 3))
# Bar graph of campaign start date count by quarter by type (Q4)
camp_typ_week_graph <- camp_typ_week %>%
ggplot(aes(x = week_of_year, y = campaign_count, fill = campaign_type)) +
geom_bar(position = "dodge", stat = "identity") +
# geom_text(aes(label = camp_typ_week$campaign_count),
# size = 3) +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Q4 Campaign Count by Week", x = "Week",
y = "Campaign Count", fill = "Campaign Type") +
scale_fill_manual(values = wes_palette("GrandBudapest1", n = 3))
# Graph of promotion types throughout the year (Q4)
weekly_campaign_sales_q4_graph <- weekly_campaign_sales_q4 %>%
ggplot(aes(x = week, y = total_sales, color = campaign_type)) +
geom_line() +
scale_y_continuous(labels = scales::dollar) +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Q4 Campaign Sales by Week", x = "Week",
y = "Campaign Sales", color = "Campaign Type") +
scale_color_manual(values = c("#F1BB7B", "#FD6467", "#5B1A18"))
# line graph of promotion types throughout the year
weekly_campaign_sales_graph <- weekly_campaign_sales %>%
ggplot(aes(x = week, y = total_sales, color = campaign_type)) +
geom_line() +
scale_y_continuous(labels = scales::dollar) +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Campaign Sales by Week", x = "Week",
y = "Campaign Sales", color = "Campaign Type") +
scale_color_manual(values = c("#F1BB7B", "#FD6467", "#5B1A18"))
gridExtra::grid.arrange(camp_typ_qtr_graph, camp_typ_week_graph,
weekly_campaign_sales_graph, weekly_campaign_sales_q4_graph,
ncol = 2)
As outlined above, there are a number of Type A, B, and C campaigns that occur through the the year and heavily in Q4. Type A campaigns continue from October through December and Type B & C campaigns occur leading up to holidays and events.
With the validation of low sales following a holiday and the understanding of campaigns before, during, and after holidays, we can now dive into the opportunity for growth for Regork.
Top Product Categories Sold
Circling back to our lowest purchase days following a major holiday, we began by evaluating what product categories customers are purchasing from on those low sale days. Taking it a step further, we evaluated what the top product categories are for each of the lowest sales days following a holiday (within 10 days).
We then evaluated the top product categories of each of the 3 types of campaigns to determine which product categories were selling the most across these campaigns.
Finally, we compared across the different campaign types to understand any commonalities existed between each of the groups.
Top product categories for lowest sales days (highlighted in yellow) do not exist in any of the top product categories for the 3 campaign types.
# Table for top type A products
camp_a_top_prod_table <- camp_a_top_prod %>%
as.data.frame() %>%
gt() %>%
tab_style(style = cell_fill(color = "#D67236"), locations = cells_column_labels()) %>%
opt_stylize(style = 5) %>%
cols_label(product_category = "Product Category",
product_occurance = "Frequency") %>%
cols_align(align = "left") %>%
tab_header(title = "Top Product Categories: Type A Campaigns",
subtitle = "Most frequently purchased product categories for Type A campaigns") %>%
tab_options(table.align = 'left', heading.background.color = "#5B1A18")
# Table for top type B products
camp_b_top_prod_table <- camp_b_top_prod %>%
as.data.frame() %>%
gt() %>%
tab_style(style = cell_fill(color = "#D67236"), locations = cells_column_labels()) %>%
opt_stylize(style = 5) %>%
cols_label(product_category = "Product Category",
product_occurance = "Frequency") %>%
cols_align(align = "left") %>%
tab_header(title = "Top Product Categories: Type B Campaigns",
subtitle = "Most frequently purchased product categories for Type B campaigns") %>%
tab_options(table.align = 'right', heading.background.color = "#5B1A18")
# Table for top type C products
camp_c_top_prod_table <- camp_c_top_prod %>%
as.data.frame() %>%
gt() %>%
tab_style(style = cell_fill(color = "#D67236"), locations = cells_column_labels()) %>%
opt_stylize(style = 5) %>%
cols_label(product_category = "Product Category",
product_occurance = "Frequency") %>%
cols_align(align = "left") %>%
tab_header(title = "Top Product Categories: Type C Campaigns",
subtitle = "Most frequently purchased product categories for Type C campaigns") %>%
tab_options(table.align = 'left', heading.background.color = "#5B1A18")
# Table for top products on lowest sales days
total_top_prods_table <- total_top_prods %>%
as.data.frame() %>%
gt() %>%
gt_highlight_rows(rows = grepl("SOFT DRINKS|FLUID MILK PRODUCTS|BAKED BREAD/BUNS/ROLLS|BAG SNACKS|SOUP|CANDY - CHECKLANE",
product_category),
fill = "#F1BB7B") %>%
tab_style(style = cell_fill(color = "#D67236"), locations = cells_column_labels()) %>%
opt_stylize(style = 5) %>%
cols_label(product_category = "Product Category",
product_occurance = "Frequency") %>%
cols_align(align = "left") %>%
tab_header(title = "Top Product Categories: Lowest Sales Days",
subtitle = "Most frequently purchased product categories for lowest sales days") %>%
tab_options(table.align = 'right', heading.background.color = "#5B1A18")
gt_two_column_layout(list(total_top_prods_table, camp_a_top_prod_table))
| Top Product Categories: Lowest Sales Days | |
| Most frequently purchased product categories for lowest sales days | |
| Product Category | Frequency |
|---|---|
| SOFT DRINKS | 1029 |
| FLUID MILK PRODUCTS | 875 |
| BAKED BREAD/BUNS/ROLLS | 733 |
| CHEESE | 649 |
| BAG SNACKS | 590 |
| SOUP | 418 |
| FRZN MEAT/MEAT DINNERS | 417 |
| CANDY - CHECKLANE | 355 |
| BEEF | 341 |
| YOGURT | 241 |
| Top Product Categories: Type A Campaigns | |
| Most frequently purchased product categories for Type A campaigns | |
| Product Category | Frequency |
|---|---|
| MAKEUP AND TREATMENT | 4807 |
| FRZN MEAT/MEAT DINNERS | 4208 |
| HAIR CARE PRODUCTS | 3831 |
| BEEF | 3314 |
| FROZEN PIZZA | 2996 |
| ICE CREAM/MILK/SHERBTS | 2637 |
| CHEESE | 2428 |
| LUNCHMEAT | 2425 |
| YOGURT | 2234 |
| ORAL HYGIENE PRODUCTS | 2226 |
gt_two_column_layout(list(camp_b_top_prod_table, camp_c_top_prod_table))
| Top Product Categories: Type B Campaigns | |
| Most frequently purchased product categories for Type B campaigns | |
| Product Category | Frequency |
|---|---|
| GREETING CARDS/WRAP/PARTY SPLY | 1343 |
| MAKEUP AND TREATMENT | 777 |
| BABY FOODS | 672 |
| FRZN MEAT/MEAT DINNERS | 586 |
| CHEESE | 532 |
| COLD CEREAL | 407 |
| REFRGRATD JUICES/DRNKS | 381 |
| FROZEN PIZZA | 351 |
| DIAPERS & DISPOSABLES | 266 |
| REFRGRATD DOUGH PRODUCTS | 249 |
| Top Product Categories: Type C Campaigns | |
| Most frequently purchased product categories for Type C campaigns | |
| Product Category | Frequency |
|---|---|
| HAIR CARE PRODUCTS | 2155 |
| DRY BN/VEG/POTATO/RICE | 792 |
| SOAP - LIQUID & BAR | 665 |
| PASTA SAUCE | 637 |
| DEODORANTS | 534 |
| SALD DRSNG/SNDWCH SPRD | 526 |
| LAUNDRY DETERGENTS | 433 |
| TEAS | 337 |
| LAUNDRY ADDITIVES | 304 |
| HAND/BODY/FACIAL PRODUCTS | 197 |
Top Product Categories Evaluated
The above tables indicates there are multiple product categories sold during the lowest sales days following a holiday that do not appear in the top product categories for the 3 campaign types (highlighted in yellow).
This introduces an opportunity to create a new campaign type targeted for post holidays.
Below continues to explore the proposed growth opportunity.
# Graph of product category sales over time
avg_low_count %>%
ggplot(aes(x = week, y = purchase_count, color = product_category)) +
geom_point(bins = 60, size = 1) +
theme(plot.title = element_text(size = 15, hjust = 0.5, face = "bold", vjust = -1),
plot.subtitle = element_text(size = 10, hjust = 0.5, face = "italic")) +
labs(color = "Product Category") +
xlab("Week of the Year") +
ylab("Product Count") +
scale_color_manual(values = c("#F1BB7B", "#FD6467", "#D67236", "#5B1A18", "#D8A499", "#7294D4")) +
geom_smooth() +
ggtitle("Product Count",
subtitle = "Total purchased by product category") +
guides(fill = "none") +
# scale_y_continuous(labels = scales::dollar) +
scale_x_continuous(breaks = seq(0, 52, 4)) +
viridis::scale_fill_viridis(option = "D")
Outside of the small dip we see for soup purchase counts throughout the summer months and the slow start we see for soft drinks at the beginning of the year (likely resulting from health trends we commonly see after New Years), the product categories sales explored above tend to stay fairly consistent during the year.
# Compare this for household and income ranges
house_comp_purchase %>%
ggplot(aes(x = product_category, y = purchase_count, fill = household_comp)) +
geom_bar(position = "dodge", stat = "identity") +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Household Composition Purchases", x = "Product Category",
y = "Purchase Count", fill = "House Composition") +
coord_flip() +
scale_fill_manual(values = wes_palette("GrandBudapest1", n = 4))
The product categories remain fairly consistent as well across different household compositions as indicated above. Although we see a variation in the amount being purchased, all compositions seems to purchase regularly from these categories.
# Compare this for household and income ranges
house_income_purchase %>%
ggplot(aes(x = product_category, y = purchase_count, fill = income)) +
geom_bar(position = "dodge", stat = "identity") +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Household Income Purchases", x = "Product Category",
y = "Purchase Count", fill = "Household Income") +
coord_flip() +
scale_fill_manual(values = c("#F1BB7B", "#FD6467", "#5B1A18", "#D67236",
"#E6A0C4", "#C6CDF7", "#D8A499", "#7294D4",
"#02401B", "#81A88D"))
We see the same consistency when reviewing household incomes. The quantity of product categories purchased vary based on income but we see the consistency of purchasing regardless of the different incomes levels.
This insight is important as it shows the value of creating a new campaign type.
Through the introduction of a new campaign type, these consistently purchased items can be targeted to help drive short-term sales increases during the time following a holiday where we normally we see sales decrease. Seeing that these products are purchased by all household compositions and incomes indicates that a campaign targeting these products would appeal to wide spread of customers. Targeting this campaign for the 10 days following a major holiday can help bridge the gap between the end of a holiday and normal shopping patterns returning to normal.
The goal of this report was to analyze how Regork can bring customers back to stores faster following a holiday. Through the data provided by The Complete Journey set we were able to identify and propose an opportunity to do just that through the implementation of a new campaign type aiming to bring shoppers in following a holiday.
Using the Transactions data set we were able to definitively establish a pattern of low transaction days following holidays. We found that of the 25 lowest sales days across 2017, 8 days were within the first 10 days following a holiday; 32% of the 25 lowest sales days.
Next, we evaluated the Campaigns and the Campaign Descriptions data sets to understand how campaigns vary during these post holiday low sales days. We discovered that all 3 campaign types occur in every quarter and while Type A campaigns are long lasting and targeted on consumer habits, Type B and C campaigns are event driven and are more common around holidays.
With the information above, we then evaluated the top 10 most frequently purchased product categories for each campaign type using the Transactions, Products, Coupons, and Campaign Descriptions data sets. We then independently evaluated the top 10 products most frequently purchased across all of the lowest transaction days following a holiday. We then cross referenced the tables to understand how they compare.
We the looked at general sales for these product categories behave over time, how they vary across income levels, and how they vary across household compositions using the Demographics, Transactions, and Products data sets.
From our data exploration, we uncovered a few key insights that led us to our proposal. The first was how the product categories sold on lowest transaction days compared to those of campaigns. We found that 6 of the top 10 product categories sold on the lowest sales days were not present in the top 10 product categories sold across Type A, B, and C campaign types.
Additionally, we found through the evaluation of the 6 product categories that they have relatively consistent sales throughout the year regardless of the time of year or holiday occurring. We found similar insights for household income and household composition. Although the quantity purchased varied, we saw that almost each category had a relatively consistent purchasing habit. The combination of consistent purchasing behavior across all types of households and incomes make it a great candidate for a new campaign as it would appeal to all customer types.
From our discovery, we propose that Regork focus on creating a targeted campaign type that focuses on frequently purchased items for low sales days following a holiday. This campaign can help drive customers back to stores faster and in turn decrease the drop in sales we consistently see following a holiday.
There are a few limitations that should be considered from the analysis we completed. First, our data set consisted of one year of information which limits our ability to analyze trends year over year. Additionally, we know very little information about each of the campaign types. More information on the design of these campaigns would allow us to better evaluate the different approaches and how they might be improved or changed. Additional information in these areas would improve the overall quality of the conclusions we can draw from our investigation.