This project focuses on using the AWS open-source AutoML library, AutoGluon, to predict bike sharing demand using the Kaggle Bike Sharing demand dataset.

This project leverages AutoGluon in AWS SageMaker Studio to predict bike sharing demand, automating model training and tuning for accurate forecasting.

This is the repository for the "Predict Bike Sharing Demand with AutoGluon" task as part of the "2. Introduction to Machine Learning" chapter of the AWS Machine Learning Engineer Nanodegree Program on Udacity

Training different models for Predicting Bike Sharing Demand by using AutoGluon's TabularPredictor.fit() on AWS SageMaker Studio

Udacity AWS ML Engineering nanodegree project - Bike Shering prediction with Autogluon

Machine learning project achieving 66% RMSE improvement in bike sharing demand prediction using AutoGluon, temporal feature engineering, and systematic hyperparameter optimization. Demonstrates iterative model development from baseline (1.32 RMSE) to optimized solution (0.45 RMSE).

This project focuses on using the AWS open-source AutoML library, AutoGluon, to predict bike sharing demand using the Kaggle Bike Sharing demand dataset.

Training a model using AutoGluon to predict bike sharing demand

Create a Kaggle account, download the Bike Sharing Demand dataset, and train a model using AutoGluon

This project aims to enhance the mobility and convenience of the public through bike-sharing programs in metropolitan areas. One of the main challenges is maintaining a consistent supply of bikes for rental.

This project predicts bike rental demand using AutoGluon, optimizing model performance through automated selection, hyperparameter tuning, and feature engineering, aiming to improve accuracy and compete in the Kaggle competition.

This project utilizes AutoGluon, AWS’s open-source AutoML framework, to predict hourly bike rental demand from the Kaggle Bike Sharing Demand dataset.