Clustering per la segmentazione dei clienti: esempio completo
Imparerete a preprocessare un dataset e-commerce, raggruppare i clienti in base a spesa e frequenza e profilare ogni segmento per ricavare insight di business.
Clustering per la segmentazione dei clienti: esempio completo è una lezione Machine Learning Academy gratuita su CoddyKit. Questa è la lezione 4 di 4. Puoi leggere la lezione completa qui gratuitamente — poi esercitati direttamente nel browser con un editor di codice integrato e un tutor IA disponibile 24/7. Fa parte del percorso di apprendimento Machine Learning Academy, e i tuoi progressi si sincronizzano tra il web e l'app CoddyKit. Il corso Machine Learning Academy include 4 lezioni in totale.
Parti di questa lezione non sono ancora state tradotte e vengono mostrate in inglese.
The Business Goal: Segment Customers
Customer segmentation groups buyers by behaviour so that marketing, product, and customer-success teams can tailor their actions to each group. Typical signals include recency (days since last purchase), frequency (number of purchases), and monetary value (total spend) — the RFM framework. Clustering discovers these segments from data without needing predefined categories.
Loading and Inspecting the Dataset
We use the classic Online Retail dataset (UCI ML Repository). It contains ~500k transactions with invoice date, customer ID, quantity, and unit price. Our first task is to load the data, drop rows with missing customer IDs, filter out returns (negative quantity), and compute the RFM features for each customer.
import pandas as pd
df = pd.read_csv('online_retail.csv', encoding='latin1')
# Drop missing customers and returns
df = df.dropna(subset=['CustomerID'])
df = df[df['Quantity'] > 0]
df['Revenue'] = df['Quantity'] * df['UnitPrice']
df['InvoiceDate'] = pd.to_datetime(df['InvoiceDate'])
print(df.shape)
print(df.dtypes)Engineering RFM Features
Recency: days since the customer's last purchase (smaller = more recent = better). Frequency: number of unique invoices. Monetary: total revenue generated. We compute these relative to a snapshot date (one day after the last transaction in the dataset) so recency increases with inactivity.
snapshot_date = df['InvoiceDate'].max() + pd.Timedelta(days=1)
rfm = df.groupby('CustomerID').agg(
Recency=('InvoiceDate', lambda x: (snapshot_date - x.max()).days),
Frequency=('InvoiceNo', 'nunique'),
Monetary=('Revenue', 'sum')
).reset_index()
print(rfm.describe())Treating Outliers and Skewness
RFM features are often highly right-skewed: a handful of VIP customers dominate the monetary axis. Before scaling, apply a log transform (np.log1p) to compress the long tail. Clip extreme outliers beyond the 99th percentile to prevent a single whale customer from distorting all centroids.
import numpy as np
for col in ['Recency', 'Frequency', 'Monetary']:
cap = rfm[col].quantile(0.99)
rfm[col] = rfm[col].clip(upper=cap)
rfm[col + '_log'] = np.log1p(rfm[col])
print(rfm[['Recency_log', 'Frequency_log', 'Monetary_log']].describe())Scaling Features for K-Means
K-Means uses Euclidean distance, so features must be on the same scale. After log-transforming, apply StandardScaler to centre each feature at zero with unit variance. Always fit the scaler on training data only — here the full RFM table since there is no separate test set for unsupervised learning.
from sklearn.preprocessing import StandardScaler
features = ['Recency_log', 'Frequency_log', 'Monetary_log']
X = rfm[features].values
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
print('Mean after scaling:', X_scaled.mean(axis=0).round(4))
print('Std after scaling:', X_scaled.std(axis=0).round(4))Selecting k with Elbow and Silhouette
Run the elbow and silhouette diagnostics on the RFM dataset to select k. For a typical e-commerce dataset you might see the elbow around k=4 or k=5, which corresponds to intuitive segments: champions, loyal customers, at-risk customers, and churned customers.
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
results = []
for k in range(2, 9):
km = KMeans(n_clusters=k, n_init=10, random_state=42)
labels = km.fit_predict(X_scaled)
results.append({'k': k, 'inertia': km.inertia_,
'silhouette': silhouette_score(X_scaled, labels)})
import pandas as pd
print(pd.DataFrame(results))Fitting the Final Clustering Model
After selecting k, fit the final K-Means model and add the cluster labels back to the RFM DataFrame. This makes it easy to compute segment profiles and build customer-facing reports. The fit_predict method fits and returns labels in one call.
from sklearn.cluster import KMeans
k = 4
km = KMeans(n_clusters=k, n_init=20, random_state=42)
rfm['Segment'] = km.fit_predict(X_scaled)
print('Cluster sizes:')
print(rfm['Segment'].value_counts())Profiling Each Segment
Compute the mean of the original (untransformed) RFM values for each cluster. This gives interpretable business profiles: Champions have low recency, high frequency, high monetary; Churned have high recency, low frequency, low monetary. Naming segments based on their profiles makes reports actionable.
profile = rfm.groupby('Segment')[['Recency', 'Frequency', 'Monetary']].mean()
print(profile.round(1))
# Optional: label segments by profile
segment_names = {
0: 'Champions',
1: 'At-Risk',
2: 'Loyal',
3: 'Churned'
}
rfm['SegmentName'] = rfm['Segment'].map(segment_names)
print(rfm['SegmentName'].value_counts())Visualising Segments with Scatter Plots
Plot Frequency vs Monetary with colour coding for each segment. Add recency as point size to encode the third dimension visually. This chart is the deliverable that a marketing team can use to identify which customers to target for reactivation campaigns vs upselling campaigns.
import matplotlib.pyplot as plt
plt.figure(figsize=(8, 5))
for seg in rfm['Segment'].unique():
mask = rfm['Segment'] == seg
plt.scatter(rfm.loc[mask, 'Frequency'],
rfm.loc[mask, 'Monetary'],
s=rfm.loc[mask, 'Recency'] + 5,
label=f'Segment {seg}', alpha=0.5)
plt.xlabel('Frequency')
plt.ylabel('Monetary')
plt.legend()
plt.title('RFM Customer Segments')
plt.show()Assigning New Customers to Segments
After deploying the model, new customers get assigned by passing their scaled RFM vector through the same scaler and then calling km.predict. Never refit the scaler on new data — use the scaler fitted on the training RFM table to avoid shifting the feature space. The centroid positions remain fixed after fitting.
import numpy as np
# Simulate a new customer: recency=10, frequency=15, monetary=600
new_customer = np.array([[10, 15, 600]])
new_log = np.log1p(new_customer)
new_scaled = scaler.transform(new_log)
segment = km.predict(new_scaled)[0]
print('New customer segment:', segment)Business Insights and Next Steps
Clustering is a starting point, not an end. After profiling segments, the team should design targeted actions: send re-engagement emails to At-Risk customers, offer loyalty rewards to Champions, present upsell offers to Loyal customers. Track conversion rates per segment to measure the ROI of segmentation. Periodically retrain the model as customer behaviour evolves over time.
Quick Check
Test your understanding of customer segmentation with clustering from this lesson.
Lesson Recap
In this lesson you learned: RFM (Recency, Frequency, Monetary) features are the standard building blocks for customer segmentation, log transformation and StandardScaler make skewed RFM features suitable for K-Means, and segment profiling translates cluster numbers into actionable business labels like Champions and At-Risk. Next up we explore PCA — a technique for reducing high-dimensional data to its most informative components.
Impara Python con un tutor IA — gratis
Scrivi ed esegui vero codice nel tuo browser, ricevi aiuto istantaneo da un tutor IA disponibile 24/7, e riprendi da dove hai lasciato sul web o nell'app.
- Corsi
- 30
- Lezioni
- 120
Domande Frequenti
La lezione «Clustering per la segmentazione dei clienti: esempio completo» è gratuita?
Sì — il testo completo di «Clustering per la segmentazione dei clienti: esempio completo» è gratuito qui sul web. Per esercitarvi in modo interattivo (un editor di codice integrato e un tutor IA 24/7) e sbloccare il resto del corso Machine Learning Academy, passa a CoddyKit PRO. Il corso Machine Learning Academy include 4 lezioni in totale.
Cosa imparerò in «Clustering per la segmentazione dei clienti: esempio completo»?
Imparerete a preprocessare un dataset e-commerce, raggruppare i clienti in base a spesa e frequenza e profilare ogni segmento per ricavare insight di business. Eserciti Machine Learning Academy con codice pratico che esegui direttamente nel browser, e un tutor IA 24/7 risponde alle tue domande mentre lavori sulla lezione.
Ho bisogno di esperienza per iniziare Machine Learning Academy?
Non è richiesta alcuna esperienza precedente. Machine Learning Academy su CoddyKit è strutturato per principianti e studenti avanzati, quindi puoi iniziare da qui o dall'inizio e procedere al tuo ritmo. Questa è la lezione 4 di 4.
Quanto tempo richiede la lezione «Clustering per la segmentazione dei clienti: esempio completo»?
La maggior parte delle lezioni CoddyKit richiede circa 5–10 minuti. Ogni lezione è breve e interattiva, quindi fai progressi costanti e riprendi esattamente da dove hai lasciato su web e app.
Posso scrivere ed eseguire codice in questa lezione Machine Learning Academy?
Sì. Ogni lezione Machine Learning Academy include un editor di codice integrato, quindi scrivi ed esegui codice reale direttamente nel tuo browser e ricevi feedback istantaneo dall'IA — nessuna configurazione locale necessaria.
Tutte le lezioni di questo corso
- K-Means: centroidi, assegnazione e aggiornamento
- Scegliere K: metodo del gomito e silhouette score
- DBSCAN: punti core, punti di bordo e rumore
- Clustering per la segmentazione dei clienti: esempio completo