Inspiration
We wanted to create a visual solution to various companies and consumers so that they are able to understand the market variability and changes that occur. We based this off of the data set that CoStar provided in order to depict the different articles relating to real estate and delve deeper into the different ways it affects a city's house value median.
What it does
This website provides an analysis of how the sentiment of articles can provide insight into how the median price of a house in a city would changed based on if the city is mentioned within the article.
How we built it
We built the backend using Tableau for making visualizations and Python for machine learning, we able use machine learning on our dataset using the ntlk library. For frontend we used CSS, Javascript, and HTML5.
Challenges we ran into
Some challenges we ran into were actually trying to understand the data that was provided to us by CoStar and trying to relate that to outside data that we might want to use. We also ran into problems with outside data limitation on real estate that was available to the public.
Accomplishments that we're proud of
We are proud that we were able to use machine learning in our project without much hassle.
What we learned
We learned the basics of the machine learning and natural language processing.
What's next for EstateBusters
By developing more data within the website, we can provide more detailed information about various real estates based on the different companies that are interested in certain cities. Furthermore, we can also delve deeper into the consumer attraction with machine learning and understand the market's goal.
Log in or sign up for Devpost to join the conversation.