Brokerage firms provide their customers insights and information on making investment decisions and the real estate market is one of them. The aim of this project is to draw insights and to develop a reliable time series model to predict housing prices in the United States with the aim of helping investors with their investment decisions.
For a full presentation and description of the project access the Modeling US Housing prices pdf file in the data files section above
Data exploration and analysis
Feature engineering and data preprocessing
Model development and training
Model perfomance and evaluation
Model prediction
The libraries used for the project include the following
pandas
numpy
matplotlib
seaborn
statsmodel
keras
tensorflow
facebook prophet
