Customer Segmentation

Run in Google Colab

Objective: Use k-Means Clustering for customer segmentation.

k-Means Clustering is an unsupervised machine learning algorithm used for partitioning data into k clusters based on their similarities. It’s a centroid-based algorithm, meaning that each cluster is represented by a central point, called the centroid or mean.

Import libraries

import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style("whitegrid")

Load the dataset

file_url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-ML0101EN-SkillsNetwork/labs/Module%204/data/Cust_Segmentation.csv"
df = pd.read_csv(file_url)
df.head()

	Customer Id	Age	Edu	Years Employed	Income	Card Debt	Other Debt	Defaulted	Address	DebtIncomeRatio
0	1	41	2	6	19	0.124	1.073	0.0	NBA001	6.3
1	2	47	1	26	100	4.582	8.218	0.0	NBA021	12.8
2	3	33	2	10	57	6.111	5.802	1.0	NBA013	20.9
3	4	29	2	4	19	0.681	0.516	0.0	NBA009	6.3
4	5	47	1	31	253	9.308	8.908	0.0	NBA008	7.2

Understand the dataset

Customer segmentation is the practice of partitioning a customer base into groups of individuals that have similar characteristics. It is a significant strategy as a business can target these specific groups of customers and effectively allocate marketing resources. For example, one group might contain customers who are high-profit and low-risk, that is, more likely to purchase products, or subscribe for a service. A business task is to retain those customers.

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 850 entries, 0 to 849
Data columns (total 10 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   Customer Id      850 non-null    int64  
 1   Age              850 non-null    int64  
 2   Edu              850 non-null    int64  
 3   Years Employed   850 non-null    int64  
 4   Income           850 non-null    int64  
 5   Card Debt        850 non-null    float64
 6   Other Debt       850 non-null    float64
 7   Defaulted        700 non-null    float64
 8   Address          850 non-null    object 
 9   DebtIncomeRatio  850 non-null    float64
dtypes: float64(4), int64(5), object(1)
memory usage: 66.5+ KB

Visualize the dataset

fig, axs = plt.subplots(3, 3, figsize=(15, 15))

for ax, feature in zip(axs.flatten(), df.drop(["Customer Id", "Address"], axis=1)):
    if len(df[feature].unique()) <= 10:
        labels, sizes = np.unique(df[feature], return_counts=True)
        sns.barplot(x=labels, y=sizes, hue=labels, ax=ax, palette="tab10", legend=False)
        ax.set_xlabel("")
        ax.set_title(feature)
    else:
        sns.histplot(data=df, x=feature, ax=ax)
        ax.set_xlabel("")
        ax.set_title(feature)

axs[2, 2].axis("off")
plt.tight_layout()
plt.show()

Preprocess the dataset

df = df.drop(["Customer Id", "Address"], axis=1)
df = df.fillna(0)
scaler = StandardScaler()
df_scaled = scaler.fit_transform(df)
df_scaled = pd.DataFrame(df_scaled, columns=df.columns)
df_scaled.head()

	Age	Edu	Years Employed	Income	Card Debt	Other Debt	Defaulted	DebtIncomeRatio
0	0.742915	0.312122	-0.378790	-0.718459	-0.683811	-0.590489	-0.523797	-0.576525
1	1.489490	-0.766349	2.573721	1.384325	1.414474	1.512962	-0.523797	0.391387
2	-0.252518	0.312122	0.211712	0.268032	2.134141	0.801704	1.909138	1.597554
3	-0.750235	0.312122	-0.674041	-0.718459	-0.421643	-0.754467	-0.523797	-0.576525
4	1.489490	-0.766349	3.311849	5.356249	3.638900	1.716094	-0.523797	-0.442507

Train the k-Means clustering

kmeans = KMeans(n_clusters=3, n_init=12)
kmeans.fit(df)

KMeans(n_clusters=3, n_init=12)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Evaluate the model

df["Label"] = kmeans.labels_
df.groupby("Label").mean()

	Age	Edu	Years Employed	Income	Card Debt	Other Debt	Defaulted	DebtIncomeRatio
Label
0	41.333333	1.956284	15.256831	83.928962	3.103639	5.765279	0.136612	10.724590
1	45.388889	2.666667	19.555556	227.166667	5.678444	10.907167	0.222222	7.322222
2	32.964561	1.614792	6.374422	31.164869	1.032541	2.104133	0.237288	10.094761

The customers in each cluster are similar to each other demographically. Now we can create a profile for each group, considering the common characteristics of each cluster. For example, the 3 clusters can be:

• AFFLUENT, EDUCATED AND OLD AGED
• MIDDLE AGED AND MIDDLE INCOME
• YOUNG AND LOW INCOME

fig = plt.figure(figsize=(10, 10))
ax = fig.add_subplot(projection='3d')
ax.scatter(df["Edu"], df["Age"], df["Income"], c=df["Label"].astype(float), cmap="viridis")
ax.set_xlabel('Education')
ax.set_ylabel('Age')
ax.set_zlabel('Income')
plt.tight_layout()
plt.show()