UI of Shanghai Second-hand House Price Prediction

This is a Course Project for Data Mining(DATA620007) in School of Data Science, Fudan University.

Requirements:

• Tensorflow 1.0.1
• Python 3.6

Training data:

Crawled from Centanet at April 2018.
The crawling part was constructed by Yan Zhiquan.

Model:

Structure: Two-hidden-layer Full Connect Neural Network with 200 nodes and ReLU for each, as well as a Dropout with keep ratio of 75%.
Epoch: 10000
MSE(on testing set): < 0.03

Example:

A simple example can be seen as follows, witch means the fair price of the dormitory we lived may worth the value up to ￥5.8 million.
The output includes the average price and the total price of the target real easte.