For our final project, we took part in a Kaggle competetion to predict the hourly bike rental demand based on weather data from the city of Washington,DC in the USA. The data for this project is available at https://www.kaggle.com/c/bike-sharing-demand
We also developed a simple front end Flask Application which can be used by the marketing team to see the demand and developed pricing according to the demand. This application was hosted on the AWS EC2.
Highlights:
We employed GridSearchCV to get the best hyperparameters for our algorithm. We used AutoML technologies like BigML and H2O AI to come up with best models for prediction. We deployed the application on Azure cloud. Check out DharitShah13.github.io for documentation.(Google Claat)