Customer Purchase Clustering and Sentiment Analysis

Aim

Apply K-Means clustering to segment customers based on their purchase behavior and use NLP techniques to preprocess text data and build a sentiment analysis model.

Description

This project involves:

1. Segmenting customers using K-Means clustering based on purchase behavior data.
2. Preprocessing text data using NLP techniques and building a sentiment analysis model.

Technologies

• Python
• Pandas
• Scikit-learn
• NLTK or SpaCy
• Matplotlib
• Seaborn

What I Learned

• Text preprocessing
• Feature engineering
• Sentiment analysis
• Clustering algorithms (K-Means)

Introduction

This project segments customers based on their purchase behavior using K-Means clustering and performs sentiment analysis on text data using NLP techniques.

Dataset

Clustering Data

The dataset includes customer purchase behavior with features such as:

• Total Purchase Amount
• Purchase Frequency
• Average Purchase Value
• Days Since Last Purchase
• Product Categories
• Total Items Purchased
• Average Items Per Purchase
• Returns Count

Sentiment Analysis Data

A separate text dataset for building and evaluating the sentiment analysis model.

Also you can find here the Google colab notebook: https://colab.research.google.com/drive/1NmltPKOOH1UzgS66iHnTVPKr3XYm297o?usp=sharing