Forecasting apartment prices using Prophet

As I moved to another state and was looking for a new apartment to rent, I started wondering: can I use Machine Learning to find seasonality patterns? Are months where rent is cheaper so I can save money before leasing an apartment?

In this project, I use Facebook Prophet, a procedure for forecasting time series data and find seasonality patterns. The results indicate that one could save up to $1000 per year on apartment rental prices by selecting the optimal time of the year to sign the apartment lease.

Jupyter Notebook

• Forecasting apartment prices using Prophet

Data Source

• Apartment List data

Time Series Forecasting

It's a supervised learning model where you have input variables (X) and an output variable (y) and you use an algorithm to learn the mapping function from the input to the output.

• x variable = datetime
• y variable = price

Authors

• @murilogustineli

Documentation

List of all libraries used in this project:

• NumPy
• Pandas
• Matplotlib
• Facebook Prophet
• BeautifulSoup
• Requests