mhghodsi / nn-to-predict-bike-sharing-rides

First project submitted as part of DL course at Coursera

Predicting Bike-Sharing Rides using Neural Network

In this project I built a Neural Network to predict bike-sharing rides.

The problem

A bike sharing ride company wants to protect how many bikes they need because if they have too few they're losing money from potential riders. At the same time If they have too many they're wasting money on bikes that are just sitting around.

Goal

The goal is to predict from historical data how many bikes they'll need in the near future using.

Solution

I built a neural network from scratch using gradient descent and backpropagation to carry out a prediction problem on a real dataset! I then trained it on historical data to make predictions.

You will be able to see the result of the NN in the charts created by the Python program.

Note: If you are running this code locally you need to make sure you have all of the libraries listed in your environment.

Note: The data comes from the UCI Machine Learning Database.