Artificial Neural Network Project: House Prices - Advanced Regression Techniques

House Prices: Advanced Regression Techniques

The goal of this project is to carry out the regression analysis of the House Sale Price for the AMES dataset available on Kaggle. We will first do an exploratory analysis of the data to figure out the dataset size, the number of variables, etc. Then we will complete some pre-proccessing and feature engineering to prepare the data, before the modeling part. We will then apply the simple linear model then the penalized models Ridge and Lasso with cross validation to select the best hyperparameter. And in a last part we will also use a single hidden layer neural network with 10 nodes.

We use for this project the following Python Libraries:

• scipy: For some basic statistis calculation
• scikit-learn: For some data preparation and classic linear regresssion
• Keras, TensorFlow: For Neural Network

Here is the link to access the notebook on Google colab. It doesn’t work directly on github.