Market Segmentation using Hierarchical Clustering
Joseph Ramirez as taught by zhenning Jimmy Xu
4/11/2025
Project Overview
This document performs hierarchical clustering analysis for market segmentation. The analysis helps identify distinct customer groups based on common characteristics, which can inform targeted marketing strategies.
Data Import and Preparation
# Load required packages
library(readr)
library(ggplot2)
# Import dataset
mydata <- read_csv('customer_segmentation.csv')## Rows: 22 Columns: 15
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (15): ID, CS_helpful, Recommend, Come_again, All_Products, Profesionalis...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.# Display the first few rows of the dataset
head(mydata)## # A tibble: 6 × 15
## ID CS_helpful Recommend Come_again All_Products Profesionalism Limitation
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 2 2 2 2 2 2
## 2 2 1 2 1 1 1 1
## 3 3 2 1 1 1 1 2
## 4 4 3 3 2 4 1 2
## 5 5 2 1 3 5 2 1
## 6 6 1 1 3 2 1 1
## # ℹ 8 more variables: Online_grocery <dbl>, delivery <dbl>, Pick_up <dbl>,
## # Find_items <dbl>, other_shops <dbl>, Gender <dbl>, Age <dbl>,
## # Education <dbl># Summary statistics
summary(mydata)## ID CS_helpful Recommend Come_again
## Min. : 1.00 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.: 6.25 1st Qu.:1.000 1st Qu.:1.000 1st Qu.:1.000
## Median :11.50 Median :1.000 Median :1.000 Median :1.000
## Mean :11.50 Mean :1.591 Mean :1.318 Mean :1.455
## 3rd Qu.:16.75 3rd Qu.:2.000 3rd Qu.:1.000 3rd Qu.:2.000
## Max. :22.00 Max. :3.000 Max. :3.000 Max. :3.000
## All_Products Profesionalism Limitation Online_grocery delivery
## Min. :1.000 Min. :1.000 Min. :1.0 Min. :1.000 Min. :1.000
## 1st Qu.:1.250 1st Qu.:1.000 1st Qu.:1.0 1st Qu.:2.000 1st Qu.:2.000
## Median :2.000 Median :1.000 Median :1.0 Median :2.000 Median :3.000
## Mean :2.091 Mean :1.409 Mean :1.5 Mean :2.273 Mean :2.409
## 3rd Qu.:2.000 3rd Qu.:2.000 3rd Qu.:2.0 3rd Qu.:3.000 3rd Qu.:3.000
## Max. :5.000 Max. :3.000 Max. :4.0 Max. :3.000 Max. :3.000
## Pick_up Find_items other_shops Gender
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:1.000 1st Qu.:1.250 1st Qu.:1.000
## Median :2.000 Median :1.000 Median :2.000 Median :1.000
## Mean :2.455 Mean :1.455 Mean :2.591 Mean :1.273
## 3rd Qu.:3.000 3rd Qu.:2.000 3rd Qu.:3.750 3rd Qu.:1.750
## Max. :5.000 Max. :3.000 Max. :5.000 Max. :2.000
## Age Education
## Min. :2.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000
## Median :2.000 Median :2.500
## Mean :2.455 Mean :3.182
## 3rd Qu.:3.000 3rd Qu.:5.000
## Max. :4.000 Max. :5.000Data Standardization
# Standardize the data (exclude ID column if present)
# Adjust the column indices as needed based on your data structure
use <- scale(mydata[,-1], center = TRUE, scale = TRUE)
# Check the result of standardization
head(use)## CS_helpful Recommend Come_again All_Products Profesionalism Limitation
## [1,] 0.5572385 1.0548991 0.7385489 -0.08536162 1.0009877 0.6236096
## [2,] -0.8049001 1.0548991 -0.6154575 -1.02433946 -0.6929915 -0.6236096
## [3,] 0.5572385 -0.4922862 -0.6154575 -1.02433946 -0.6929915 0.6236096
## [4,] 1.9193772 2.6020844 0.7385489 1.79259406 -0.6929915 0.6236096
## [5,] 0.5572385 -0.4922862 2.0925553 2.73157191 1.0009877 -0.6236096
## [6,] -0.8049001 -0.4922862 2.0925553 -0.08536162 -0.6929915 -0.6236096
## Online_grocery delivery Pick_up Find_items other_shops Gender
## [1,] -0.3554390 0.8049001 1.4623535 -0.6774335 -0.4212692 -0.598293
## [2,] -0.3554390 0.8049001 0.5161248 -0.6774335 -0.4212692 -0.598293
## [3,] 0.9478374 0.8049001 -0.4301040 -0.6774335 0.2916479 -0.598293
## [4,] 0.9478374 0.8049001 -0.4301040 0.8129201 -0.4212692 -0.598293
## [5,] -0.3554390 0.8049001 -1.3763327 0.8129201 0.2916479 1.595448
## [6,] -1.6587154 -0.5572385 -1.3763327 -0.6774335 1.0045650 -0.598293
## Age Education
## [1,] -0.6154575 -0.7284586
## [2,] -0.6154575 -0.7284586
## [3,] -0.6154575 -0.7284586
## [4,] 0.7385489 1.1207055
## [5,] 2.0925553 -0.7284586
## [6,] -0.6154575 1.1207055Hierarchical Clustering Analysis
# Calculate distance matrix
dist_matrix <- dist(use)
# Apply hierarchical clustering
seg.hclust <- hclust(dist_matrix)
# Plot dendrogram
plot(seg.hclust, main = "Hierarchical Clustering Dendrogram",
xlab = "Observations", sub = "", cex = 0.6)
# Add colored rectangles to highlight clusters
rect.hclust(seg.hclust, k = 3, border = "red")
Identifying Cluster Memberships
# Cut tree to form 3 clusters
# You can adjust the number of clusters based on your analysis
groups.3 <- cutree(seg.hclust, 3)
# Count observations in each cluster
table(groups.3)## groups.3
## 1 2 3
## 17 3 2# Find members in each cluster
cluster1_members <- mydata$ID[groups.3 == 1]
cluster2_members <- mydata$ID[groups.3 == 2]
cluster3_members <- mydata$ID[groups.3 == 3]
# Display the first few members of each cluster
head(cluster1_members)## [1] 1 2 3 6 7 8head(cluster2_members)## [1] 4 20 22head(cluster3_members)## [1] 5 19Analyzing Cluster Characteristics
# Calculate mean values for each variable by cluster
cluster_means <- aggregate(mydata[,-1], list(Cluster = groups.3), mean)
print(cluster_means)## Cluster CS_helpful Recommend Come_again All_Products Profesionalism
## 1 1 1.294118 1.117647 1.235294 1.823529 1.235294
## 2 2 2.666667 2.666667 2.000000 2.333333 2.000000
## 3 3 2.500000 1.000000 2.500000 4.000000 2.000000
## Limitation Online_grocery delivery Pick_up Find_items other_shops Gender
## 1 1.352941 2.235294 2.235294 2.705882 1.294118 2.647059 1.176471
## 2 1.666667 3.000000 3.000000 2.000000 1.666667 2.333333 1.333333
## 3 2.500000 1.500000 3.000000 1.000000 2.500000 2.500000 2.000000
## Age Education
## 1 2.411765 3.117647
## 2 2.333333 4.333333
## 3 3.000000 2.000000# Calculate median values for each variable by cluster
cluster_medians <- aggregate(mydata[,-1], list(Cluster = groups.3), median)
print(cluster_medians)## Cluster CS_helpful Recommend Come_again All_Products Profesionalism
## 1 1 1.0 1 1.0 2 1
## 2 2 3.0 3 2.0 2 2
## 3 3 2.5 1 2.5 4 2
## Limitation Online_grocery delivery Pick_up Find_items other_shops Gender Age
## 1 1.0 2.0 2 3 1.0 2.0 1 2
## 2 2.0 3.0 3 2 2.0 2.0 1 2
## 3 2.5 1.5 3 1 2.5 2.5 2 3
## Education
## 1 2
## 2 5
## 3 2# Visualize differences between clusters
# Choose a few key variables for visualization
key_vars <- names(mydata[,-1])[1:3] # Adjust indices as needed
# Create a function to plot cluster differences
plot_cluster_diff <- function(var_name) {
boxplot(mydata[[var_name]] ~ groups.3,
main = paste("Distribution of", var_name, "by Cluster"),
xlab = "Cluster", ylab = var_name)
}
# Apply the function to key variables
for (var in key_vars) {
plot_cluster_diff(var)
}
Principal Component Analysis (Optional)
# Perform PCA
pca_result <- prcomp(use, scale = TRUE)
# Summary of PCA
summary(pca_result)
# Plot the first two principal components with cluster colors
pca_data <- as.data.frame(pca_result$x[,1:2])
pca_data$cluster <- as.factor(groups.3)
ggplot(pca_data, aes(x = PC1, y = PC2, color = cluster)) +
geom_point(alpha = 0.7) +
theme_minimal() +
labs(title = "PCA Plot with Cluster Assignment",
x = "Principal Component 1",
y = "Principal Component 2")Export Results
# Export cluster assignments
write.csv(data.frame(ID = mydata$ID, Cluster = groups.3),
"cluster_assignments.csv", row.names = FALSE)
# Export cluster statistics
write.csv(cluster_means, "cluster_means.csv", row.names = FALSE)
write.csv(cluster_medians, "cluster_medians.csv", row.names = FALSE)