Zillow is an online American real estate database with the purpose of empowering consumers with information helping them make informed decisions for buying, selling and renting properties.

Aim: To predict the Selling Price of properties by using the available “Last Sold Price” of properties on Zillow in multiple neighborhoods of different cities.

Primary Data Source

We would be using 2 zillow api’s as our primary data source:

• Deepcomps : To get detail of properties like size, are, last sold price, etc. within a neighbourhood for a given Zillow Property ID(ZPID)

• DeepSearchResults : To get multiple ZPID’s using address, zipcode, city and addresses of properties.

Secondary Data Source

To fetch multiple ZPID’s by providing addresses, we plan to use Zillow website/Publicly available verified addresses, as secondary data sources

Problem Description

Whenever a property holder wants to sell his property, below are some of the issues faced:

• may not be aware of the current price of the property
• may not know comparable prices of similar kind of properties in the area

Analytics plan

• Data Cleaning
• Descriptive analysis(Correlation matrix, histogram)
• Predictive analysis (Linear Regression, Decision Tree, Random Forest)

The output of our analysis is the predicted selling price of a property. By running all the machine learning models, we would analyse our results:

• By comparing models using RMSE and R-square values
• Plotting correlation matrix and histograms to see the distribution and dependencies among variables.