Or the home you would like to buy. Using Zillow forecasts, I obtained the following predictions, clearly indicating strong recovery for the West Coast, according to Zillow.

You can easily retrieve this data by entering a city on Zillow's location box, then clicking on any home for sale on that city. The task could be automated with a web crawler or using an intern. And once you gathered data for 1,000 locations you can then interpolate for all 30,000 zip codes.

Expected home value increase 12 months from now:

The main questions, for a data scientist, are:

• What methodology does Zillow use (read answer here)
• How frequently is the data / forecast updated
• What are the confidence intervals?
• How robust are these forecasts? Are they inflation-adjusted?

It would be interesting to plot this data (in a nice map), and maybe doing some interpolation to get a reliable forecast for each of the 30,000 US zip codes, broken down per type of property (expensive, medium, cheap).

Related articles

• Questioning Zillow estimates and their statistical methodology
• Yelp hit with a class action lawsuit for its rotten data mining alg...
• Macy's thinks that their customers are innumerate
• How could Amazon increase sales by redefining relevancy?
• How do you estimate the proportion of bogus accounts on Facebook?
• Zip code data (available for download)
• Data Science Resources