1. Introduction

Business Problem

Regork regularly offers discounts through retailer and manufacturer promotions, but not all discounts result in higher customer spending. Understanding the effectiveness of different discount strategies can help optimize pricing and promotional campaigns to maximize revenue while maintaining profit margins.

This analysis addresses: 1. How do different types of discounts impact overall revenue? 2. Which product categories benefit most from discount strategies? 3. How does customer demographic influence discount effectiveness?

Approach

  • Merge transactions, discount details, and demographic data.
  • Compare customer spending behavior under different discount strategies.
  • Identify which products and customer segments respond best to discounts.

Impact for Regork CEO

By optimizing discount strategies, Regork can: - Increase revenue without excessive margin losses. - Design targeted promotions to maximize customer engagement. - Reduce ineffective discounting practices that do not lead to higher spending.

2. Data Overview

Utilizing the following datasets from Complete Journey: - Transactions: Purchase records including discount details. - Coupons: Information on manufacturer and retailer discounts. - Demographics: Household data to analyze discount effectiveness across different customer segments.

# Load necessary datasets
transactions <- get_transactions()

# Merge transaction data with coupon and demographic information
df <- transactions %>%
  left_join(products, by = "product_id") %>%  # Include product categories
  left_join(coupons, by = "product_id") %>%
  left_join(demographics, by = "household_id", keep = TRUE) %>%
  mutate(total_discount = replace_na(retail_disc, 0) + replace_na(coupon_match_disc, 0))

3. Discount Strategy Analysis

Impact of Discounts on Total Revenue

discount_revenue <- df %>%
  mutate(has_discount = ifelse(total_discount > 0, "Discount Applied", "No Discount")) %>%
  group_by(has_discount) %>%
  summarise(total_sales = sum(sales_value, na.rm = TRUE))

# Bar chart for revenue impact of discounts
ggplot(discount_revenue, aes(x = has_discount, y = total_sales, fill = has_discount)) +
  geom_bar(stat = "identity") +
  labs(title = "Impact of Discounts on Total Revenue",
       x = "Discount Applied", y = "Total Revenue") +
  theme_minimal() +
  scale_y_continuous(labels = scales::comma)

Top Product Categories Benefiting from Discounts

discount_products <- df %>%
  filter(total_discount > 0) %>%
  group_by(product_category) %>%
  summarise(total_discounted_sales = sum(sales_value, na.rm = TRUE)) %>%
  arrange(desc(total_discounted_sales)) %>%
  head(10)

# Bar chart for product categories benefiting from discounts
ggplot(discount_products, aes(x = reorder(product_category, -total_discounted_sales), y = total_discounted_sales, fill = product_category)) +
  geom_bar(stat = "identity") +
  labs(title = "Top Product Categories Benefiting from Discounts",
       x = "Product Category", y = "Total Sales with Discounts") +
  theme_minimal() +
  coord_flip() +
  scale_y_continuous(labels = scales::comma)

Demographic Response to Discounts

discount_demographics <- df %>%
  filter(total_discount > 0, !is.na(age), !is.na(income)) %>%
  group_by(age, income) %>%
  summarise(total_spent_with_discounts = sum(sales_value, na.rm = TRUE))

# Heatmap for demographic response to discounts
ggplot(discount_demographics, aes(x = age, y = income, fill = total_spent_with_discounts)) +
  geom_tile() +
  labs(title = "Demographic Response to Discount Strategies",
       x = "Age Group", y = "Income Group") +
  scale_fill_gradient(low = "lightblue", high = "darkblue", labels = scales::comma) +
  theme_minimal()

4. Key Insights & Recommendations

Findings

  1. Discounts increase total revenue, but excessive discounts may not proportionally increase profits.
  2. Certain product categories benefit more from discounts, making them strong candidates for targeted promotions.
  3. Customer demographics influence discount effectiveness, suggesting personalized pricing strategies could maximize returns.

Actionable Solutions

1. Optimize Discount Levels for Maximum Profitability

  • Analyze margin impact of discounts to determine the most profitable threshold.
  • Reduce deep discounting on products that already sell well.

2. Focus Discounts on High-Impact Product Categories

  • Target high-revenue product categories with strategic discounts.
  • Pair discounted items with full-priced complementary products.

3. Implement Personalized Discount Strategies

  • Use demographic insights to tailor discount offers.
  • Offer digital and loyalty-based discounts to encourage repeat purchases.

5. Summary

Summary of Problem Addressed

This report analyzed how different discount strategies impact customer spending and revenue, helping Regork optimize promotions for better profitability. By merging transaction data with coupon and demographic details it was possible to analyze the impact of discounts on revenue, and assess customer responsiveness to price reductions.

Proposed Actions for the CEO

  • Optimize discount levels to maximize profit without excessive reductions.
  • Target high-impact product categories with strategic discounting.
  • Personalize discount strategies to match customer demographic preferences.