REFerence Sheet (Real Estate Financial)

• 

  REFerence Sheet dashboard

• 

  REFerence Sheet snapshot 2

Inspiration

We were inspired by the popularity of real estate resources like Zillow, so we decided to explore data from their listings and provide potential renters with the information they need while deciding on a property.

What it does

REFerence Sheet provides a price estimate based on details of a certain property, such as the number of beds, number of baths, and total area (in square feet). A machine learning algorithm was applied to local real estate data to help predict housing prices. The dashboard also implements multiple data visualization strategies to communicate details of a property that have an effect on the listing price, as well as comparisons between these details to inform the user before they make a financial decision.

How we built it

We built this project using Python and JupyterDash, as well as Google Colab.

Challenges we ran into

We initially wanted to scrape Zillow data using Java, store it using MongoDB, and access that database using Python. However, we found Zillow listings cannot be easily web-scraped with Java, but can be using Python and a special API Key from Scrapeak's Zillow Scraper API. We also initially wanted to create a functioning web app but found that the connection failed for the port and server, so we decided to keep it as a dashboard that can be run within Jupyter Notebooks/Google Colab.

Accomplishments that we're proud of

We are proudest of the finished dashboard and UI of REFerence Sheet, as well as the utilization of JupyterDash, something we've never used before, to create it. We are also proud of our ability to scrape Zillow data after all when that was proving to be difficult at first.

What we learned

The biggest thing we learned was how to look at real estate data and derive meaning from what is already there. The second biggest thing we learned was how to apply machine learning to something like this, whether it's testing models or integrating it within the interactive dashboard.

What's next for REFerence Sheet

With more time, we would have wanted to take more data, run it through machine learning models, and use it to predict the efficacy of a financial investment in the real estate sector.

Built With

• colab
• jupyterdash
• jupyternotebooks
• python
• scrapeak