Predicting House Prices with Keras

This workflow demonstrates how to solve a regression problem - predict numeric values - with a simple Keras neural network on the example of house sale price prediction.

First, the data are partitioned to the training and test sets. Then, missing values are handled, numerical features are normalized and one hot encoding is applied to the categorical features. A simple neural network is assembeled and trained using Keras nodes. The model is then applied to the test set and evaluated.

External resources

• House Prices Dataset