Consumer Shopping Channel Analysis

A data science project analyzing consumer shopping behavior across online and offline channels. This project explores purchasing patterns, customer segmentation, and predictive modeling to generate actionable business insights.

---

Project Overview

• Goal: Understand how consumers choose shopping channels and what drives their behavior
• Scope: End-to-end data science workflow (EDA -> modeling -> insights)
• Dataset: Simulated 2026 consumer behavior dataset
• Tools: Python, Pandas, Scikit-learn, Matplotlib, Seaborn

---

Key Questions

• How do demographics influence shopping preferences?
• What factors drive online vs. in-store purchases?
• Can we predict customer shopping behavior?
• How can businesses segment customers effectively?

---

Project Structure

Main Notebook

consumer.ipynb - Complete analysis pipeline:

Section	Topic
0	Setup & Imports
1	Data Loading & Overview
2	Data Cleaning
3	Demographic Analysis
4	Purchase Behavior
5	Channel Preferences
6	Product Category Trends
7	Seasonal Patterns
8	Spending Analysis
9	Customer Segmentation
10	Correlation Analysis
11	Predictive Modeling
12	Model Evaluation
13	Key Insights
14	Conclusions & Recommendations

---

Live Demo

View Full HTML Report

---

Data

• Consumer_Shopping_Trends_2026.csv - Primary dataset

---

Methodology

1. Data Preprocessing

• Handling missing values
• Encoding categorical variables
• Feature scaling

2. Exploratory Data Analysis (EDA)

• Distribution analysis
• Demographic insights
• Channel usage patterns

3. Feature Engineering

• Behavioral indicators
• Spending patterns

4. Modeling

• Logistic Regression
• Random Forest
• Clustering

5. Evaluation

• Accuracy, Precision, Recall
• Confusion Matrix

---

Key Insights

• Younger consumers prefer online channels
• High-income users spend more per transaction
• Segmentation reveals distinct behavior clusters

---

How to Run

jupyter notebook consumer.ipynb

---

Author

Danbo Chen PhD @ OSU | Data Science | Machine Learning