🚀 Welcome to the YouTube Data Analysis and Insights project! 📊

The second iteration of Cuana, an E2E customer analytics solution for churn/CLV prediction, segmentation & lead scoring

Optimize marketing strategies and enhance decision-making. Explore customer data, segment behavior, calculate CLV, analyze demographics, and visualize insights. 🚀

This project dives deep into customer sales data to uncover valuable insights for business decision-making. It leverages machine learning and time-series forecasting to predict customer churn, forecast product demand, and segment customers based on their purchasing behavior.

The team developed a Sales Forecasting Analytics System for NSF Global Sdn. Bhd., improving data-driven decision-making. They processed and cleaned datasets, implemented Prophet for time series forecasting, and designed interactive visualizations. Automating the data pipeline reduced processing time and project delivery efficiency.

RFM model-based Customer Segmentation using Clustering, Classification and BTYD Models

Demonstrates how Python's lifetimes package can identify high-value customers and predict their future purchasing behavior. Utilizing the BG/NBD model to forecast purchase frequency and the Gamma-Gamma model to estimate transaction value, this repository aids in crafting targeted marketing strategies.

This project leverages RFM analysis, KMeans clustering, and probabilistic models (BG/NBD and Gamma-Gamma) to segment customers and estimate Customer Lifetime Value (CLV) using the Online Retail II dataset. It also integrates XGBoost models to predict future purchasing behavior and CLV, with interactive visualizations via a Streamlit dashboard.

Performed cohort analysis to boost retention & revenue via SQL insights on customer retention, revenue retention, & CLV by product category, with actionable strategies for high-value categories.

A Streamlit-based dashboard that predicts a customer's future spending in the next 3 and 6 months, classifies customer type (Retail or Wholesaler), and visualizes their past purchasing behavior using transactional data.

This project performs cohort analysis to estimate Customer Lifetime Value (CLV) by analyzing weekly revenue and user registrations over 12 weeks, forecasting future revenue, and providing actionable insights for marketing and business strategy.

Final project of the International Master in Data Science in which our team develop marketing strategies for a fashion retail company targeted at specific customer segments and provide them with customized offers. The segmentation was done by employing RFM analysis in conjunction with unsupervised clustering algorithms.

Customer Retention and Lifetime Value Analysis Using Cohort Analysis on AdventureWorks Dataset (2011-2014)

This project explores customer behavior in a large e-commerce dataset, uncovering comprehensive CRM data analysis, data preprocessing and EDA techniques to refine customer interaction, and implemented RFM scoring for dynamic customer segmentation, revealing actionable insights on purchasing patterns.

An end-to-end customer analytics project using the Online Retail II dataset. This work features RFM segmentation, churn prediction with XGBoost, Customer Lifetime Value (CLV) forecasting with BG/NBD & Gamma-Gamma models, and statistical A/B testing.

A data science project leveraging Python and Scikit-Learn to build predictive models that estimate customer lifetime value (CLV). Includes data cleaning, feature engineering, and model selection to identify key drivers of CLV, supporting strategic decision-making in customer retention and marketing.

This repository analyzes global e-commerce trends and their effects on traditional retail. It includes data preprocessing, Customer Lifetime Value (CLV) calculations, and What-if analyses to explore pricing strategies, providing insights into the evolving retail landscape.

The Global E-commerce & Retail Analysis project involves data preprocessing, dimensionality reduction with PCA, CLV calculation and What-If analysis . Key insights include effective PCA for data reduction, detailed CLV analysis across segments , and the impact of pricing strategies on sales.

This project analyses customer retention, churn and customer lifetime value (CLV) on the Google Merch Shop, focusing on weekly behaviour trends and CLV predictions. The findings identify key factors impacting retention, CLV, and customer acquisition cost (CAC) effectiveness.