README.md

Dannjs San-Francisco Live Demo

A Deep Neural Network learns to predict housing prices in San-Francisco

Dataset

The dataset consists of 9 parameters about residential city blocks. Green dots represent low prices, Red dots represent high prices. The moving dots are the models predictions.

Data has been normalized, and formatted into JSON. The original dataset accounts for the entirety of california, it has been scaled down to only San-Francisco.

The original dataset can be found here

Data fed to the neural network:

1. longitude
2. latitude
3. housing_median_age
4. total_rooms
5. total_bedrooms
6. population
7. households
8. median_income
9. ocean_proximity

Data the neural network is tasked to predict:

1. median_house_value

Run

Launch canvas.html into any browser, or click here

Tutorial

A tutorial to create this in Node.js is available here.