We use two models including ridge regression and neural network.

​

Ridge regression is often used to analyze multiple regression data that suffer from multicollinearity. It is based on L2 regularization. By using ridge regression, model variance can be decreased when new data is used. In this project, scikit-learn package is used to generate ridge regression model.

 

Neural network is a class of machine learning algorithms that use a cascade of multiple layers of nonlinear processing units including ReLU and sigmoid function for feature extraction and transformation. By constructing neural network, more complex supervising learning problems can be solved. In this project, tensorflow package is used to build neural network architecture.