model lane
The Cost of Living, a Zillow Housing Forecast
A three-person team project modeling housing-affordability trends across U.S. states from 2000 to 2020, using time-series methods and Bayesian hierarchical modeling on Zillow price and CPS demographic data.
pipeline
- data (covered)
- model (covered)
- eval (covered)
- serve (not covered)
- monitor (not covered)
PythonPyMC3statsmodelsscikit-learnpandasNumPySciPy
linksAs part of a three-person team, I modeled housing-affordability trends using clustering, time-series methods (ARIMA and Kalman filtering), and Bayesian hierarchical modeling on Zillow price and CPS demographic data.
I personally built the Bayesian-modeling and regression components, which we used to evaluate how demographics correlate with the variation between regional markets.