Predictive Customer Behaviour Modelling (RFM + Regression)

Overview

This project applies RFM analysis and regression techniques to model customer behaviour and value. It focuses on transforming transactional data into meaningful features that support predictive marketing analytics.

Objectives

• Clean and prepare customer transaction data
• Engineer RFM-based customer features
• Build regression-based predictive models
• Evaluate customer behaviour patterns
• Generate actionable business insights

Dataset

This project uses customer transaction data for RFM feature construction and predictive modelling.

Tools & Technologies

• Python
• Pandas & NumPy
• Matplotlib
• Scikit-learn
• Jupyter Notebook

Project Structure

predictive-customer-behaviour-rfm-regression/ ├── data/raw/ ├── notebooks/ ├── outputs/ ├── README.md └── requirements.txt

Methodology

1. Data Loading & Cleaning
2. RFM Feature Engineering
3. Exploratory Data Analysis
4. Regression Modelling
5. Model Evaluation
6. Insights & Recommendations

Results

The project demonstrates how customer transaction behaviour can be converted into predictive features for modelling customer value and behavioural trends.

Business Value

This analysis supports customer targeting, retention planning, and data-driven decision-making in marketing and CRM contexts.

How to Run

1. Clone the repository
2. Install dependencies: pip install -r requirements.txt
3. Open the notebook in the notebooks/ folder
4. Run all cells

Author

Chinwe Azikiwe