Customer Segmentation using K-Means Clustering

# File Name: customer_segmentation_kmeans.R

# Author: Gerard King - www.gerardking.dev

# Title: Customer Segmentation using K-Means Clustering

# Description: This program uses k-means clustering to segment customers into different groups based on their

# age, income, and spending score. Customer segmentation is widely used in banking to target specific customer

# groups with tailored marketing or financial products.

# Use Cases:

# - Segmenting customers for personalized marketing or product offerings

# - Identifying high-value customers for VIP services

# - Grouping customers based on behavior or financial health

# Audience:

# - Marketing analysts and data scientists working in banking and finance

# - Customer experience teams looking to tailor offerings to different customer segments

# - Business analysts interested in customer grouping for targeted interventions

# Blue Team Uses:

# - Grouping customers based on financial behaviors to target fraud prevention efforts

# - Identifying potential customers for high-risk behavior based on transaction patterns

# - Analyzing customer financial health across different segments to improve services

# Red Team Uses:

# - Segmenting attack data to find potential targets based on vulnerability patterns

# - Analyzing network behavior to cluster types of fraud or anomalous activities

# - Identifying common patterns in customer behavior that could lead to exploitation

# Current Date: 2025-03-06

# Load necessary libraries

library(ggplot2)

library(cluster)

# Set the seed for reproducibility

set.seed(606)

# Generate synthetic customer data (age, income, spending score)

n <- 500  # number of customers

age <- sample(18:70, n, replace = TRUE)

income <- rnorm(n, mean = 50000, sd = 20000)

spending_score <- sample(1:100, n, replace = TRUE)  # Spending score from 1 to 100

customer_data <- data.frame(age, income, spending_score)

# Standardize the data (important for k-means clustering)

customer_data_scaled <- scale(customer_data)

# Perform k-means clustering with 4 clusters (k = 4)

kmeans_result <- kmeans(customer_data_scaled, centers = 4)

# Add cluster assignment to the dataset

customer_data$cluster <- as.factor(kmeans_result$cluster)

# Visualize the customer clusters using ggplot2 (Age vs Spending Score)

ggplot(customer_data, aes(x = age, y = spending_score, color = cluster)) +

  geom_point(size = 3) +

  labs(title = "Customer Segmentation: Age vs Spending Score", 

       x = "Age", y = "Spending Score", color = "Customer Segment") +

  scale_color_manual(values = c("red", "blue", "green", "purple")) +

  theme_minimal()

# Display the cluster centers

cat("Cluster Centers:\n")

print(kmeans_result$centers)

# Print the current date for reference

cat("Date of execution:", Sys.Date(), "\n")