This repository contains the code and analysis for a machine learning project aimed at predicting Customer Lifetime Value (CLV) in an e-commerce context. The project utilizes a range of machine learning models to forecast the total revenue a business can expect from a customer throughout their relationship.
The goal of this project is to build a predictive model that can accurately forecast the Customer Lifetime Value (CLV) for an e-commerce business. Accurate predictions of CLV assist businesses in optimizing marketing strategies, focusing on customer retention, and efficiently allocating resources toward the most valuable customers.
The project is based on the "Online Retail II" dataset from the UCI Machine Learning Repository, which includes transactional data of a UK-based online retailer from December 2009 to December 2011.
- Perform exploratory data analysis to understand customer purchasing behavior.
- Develop predictive models for CLV and compare their performance.
- Extract actionable insights to guide marketing and business strategies.
The project explores several machine learning models:
- Linear Regression (Baseline Model)
- Decision Tree Regressor
- Random Forest Regressor
- Gradient Boosting Regressor
- Neural Network (Multilayer Perceptron)
Each model's performance is evaluated based on RMSE (Root Mean Square Error) and R-squared metrics.