Uber's Two-Tower model for Uber Eats restaurant recommendations | Eric Seufert posted on the topic | LinkedIn
🚀 During a project at the National Telecommunication Institute, a team developed an "Uber Ride Cancellation Prediction Model" using machine learning to minimize ride cancellations. Key data points included booking value, trip distance, ratings, vehicle type, payment method, and timing. They used models like Logistic Regression and Random Forest, with Random Forest achieving the best results. A Streamlit app was created to predict ride outcomes and generate reports. This project enhanced skills in data preprocessing, model evaluation, and app development.
Share