Bike Sharing Prediction

In this project, I built a neural network from scratch to carry out a prediction problem on a real dataset that comes from the UCI Machine Learning Database. It's one of my Udacity projects that I have made to improve my skills in building a neural network from the ground up.

Result preview

As we can see, the model overestimates bike ridership in December because it hasn't had sufficient holiday season training examples. The predictions generally are quite accurate, though!