This project focuses on customer segmentation using RFM analysis and K-Means clustering into high value, low value, and potentially loyal groups. Key revenue metrics such as LastMonthRevenue and LifeTimeRevenue are calculated, with visualizations to provide insights into customer behavior for targeted marketing and improved retention str

☎️ Identify customer behavior who likely to churn and make a predictive model that will classify if customer will churn or not

This project analyzes user data from the MetroCar ride-hailing platform, focusing on user engagement, ride requests, cancellations, and driver performance. The aim is to identify areas for improvement and provide actionable insights to enhance the overall user experience.

This notebook focuses on RFM (Recency, Frequency, Monetary) segmentation, a popular method used in customer analysis to group customers based on their purchasing behavior. The key goal of RFM segmentation is to identify different customer segments by analyzing their transaction history and assigning them to categories based on their recency of purc

Applies Principal Component Analysis (PCA) to dimensionality reduction using Python, SQL, and GBQ.

A machine learning project that predicts online shopping purchase intent using a k-nearest neighbor classifier. The model analyzes visitor behavior features like page visits, browsing duration, bounce rates, and user characteristics to predict whether a visitor will make a purchase. Built with scikit-learn.

This repository contains configuration files for analysing & visualising data obtained from Southern Prefecture Restaurant.

MusicBox user behavior(play, download, search) analysis and churn prediction(Python, Spark)

Leveraging K-Means clustering, our project categorizes retail customers based on purchasing behaviors and demographics. This provides businesses with actionable insights to tailor marketing efforts, enhancing customer experience and boosting sales.

This project analyzes user data from the MetroCar ride-hailing platform, focusing on user engagement, ride requests, cancellations, and driver performance. The aim is to identify areas for improvement and provide actionable insights to enhance the overall user experience.

This repository contains the analysis of Iowa liquor retail sales data, aimed at uncovering sales trends and forecasting future sales patterns. The project involves data cleaning, preparation, and advanced time series analysis using Microsoft SQL Server and Google Colab.

Machine Learning based Customer Behaviour Prediction

The project provides the Apriori algorithm and Market Basket Analysis (MBA) to analyze transactional data, generating personalized recommendations based on Support, Confidence, and Lift metrics to enhance customer experience and boost sales.

Key: clustering, using logistic regression to build elasticity modeling for purchase probability, brand choice, and purchase quantity & deep neural network to build a black-box model to predict future customer behaviors.

Multivariate Time Series Classification for Human Activity Recognition with LSTM

R package for Customer Behavior Analysis