Clustering is an unsupervised machine learning technique that groups customers into meaningful segments based on similarities in behavior or attributes. This lesson explains clustering basics, popular algorithms, and business applications for personalized marketing and customer insights.
Clustering is about finding natural groupings in data without pre-defined labels. In business, it helps segment customers who behave similarly, enabling targeted strategies.
A retail chain applies K-Means on customer data (age, income, spending score) to discover high-spenders, budget shoppers, and loyal customers.
Create campaigns tailored for high-value customers, discount seekers, or loyal members.
Suggest products based on similarities between customers’ past purchases.
Understand different customer groups to design better pricing and product strategies.
Identify at-risk groups and run loyalty programs to reduce churn.
from sklearn.cluster import KMeans
import pandas as pd
# Sample data
data = {'Age': [22,25,30,40,35,50,23,45],
'Income': [30000,40000,50000,80000,75000,100000,32000,85000]}
df = pd.DataFrame(data)
# Apply KMeans
kmeans = KMeans(n_clusters=3, random_state=42)
df['Cluster'] = kmeans.fit_predict(df[['Age','Income']])
print(df)
This example groups customers into 3 clusters based on Age and Income. Businesses can then tailor offers for each segment.