This project analyzes a year of Cyclistic bike-share data to uncover the differences in riding habits between casual riders and annual members. The goal is to provide business insights that can help Cyclistic design marketing strategies to convert casual riders into members and ultimately increase long-term revenue!
Read Blog PostA machine learning model built in VS Code and deployed with Streamlit that predicts customer churn using input features. The data we used reflects from the telecom industry and can predict churn with just Age, Monthly Charges, Gender, and Tenure!
View Web App | View CodeA project in development that integrates SQL, Python machine learning, and Tableau dashboards for fraud detection analysis. Check back soon for updates!