The first step of our model training involved dividing the data into two sets. The training set and the testing set. The testing set is primarily used for model evaluation to see how well our model is performing.

Then we preprocessed and scaled the data between the range of 0 and 1 using Scikit-learn, a machine learning library for Python. Having large values can cause biases in our model. As a result, we normalized the data to fit into our model. Next, to build the neural network we utilized Tensorflow to import the Sequential and the Dense module. The Sequential module allows you to build the model layer by layer. And the Dense module is used to connect the layer to one another inside a network where we can define the number of neurons each layer should contain.

Our model also needs an activation function. The one that we are using for this project is the rectified linear activation function or ReLU.

ReLU is a linear function that will output the input directly if it is positive, otherwise, it will output zero. Lastly, to compile the model we integrated an optimizer for specifying the gradient descent and the loss function to evaluate how well our algorithm can model the given data.