[WEEK 1 — Prediction Of Real Estate Price]
Team Members: Kübra Hanköylü, Ufuk Baran Karakaya, Emre Dağıstan, Tolga Kesemen
This is the first blog post of our project. It will give a brief information about the project and the approach.
Introduction
A home is often the largest and most expensive purchase a person makes in his or her lifetime. Therefore, the real estate market is an important part of the economy. The global real estate market size is estimated to be USD 3,505.2 billion by 2016 owing to the increasing population and demand for personal household space is pushing the market for a healthy growth in the forecast period. Especially, the USA has the most developed real estate sector of the world.
Zillow is the leading real estate and rental marketplace dedicated to empowering consumers with data, inspiration and knowledge around the place they call home, and connecting them with the best local professionals who can help.
Zillow serves the full lifecycle of owning and living in a home: buying, selling, renting, financing, remodeling and more. It starts with Zillow’s living database of more than 110 million U.S. homes — including homes for sale, homes for rent and homes not currently on the market, as well as Zestimate home values, Rent Zestimates and other home-related information. Zillow operates the most popular suite of mobile real estate apps, with more than two dozen apps across all major platforms. [1]
What is our aim?
There is a competition on Kaggle which is supported by Zillow to improve their prediction accuracy for real estates named as “Zestimate”.
In currently, Zestimate based on 7.5 million statistical and machine learning models that analyze hundreds of data points on each property.
Although the competition was finished, we also want to make a run about it.
The Dataset
We are going to use Zillow’s dataset. The dataset contains information about roughly three millions of houses. Each of house has fifty-eight features like; regions, bedroom count, year of construction etc.
In this project, we might use the following methods: Deep Learning, XGBoost, Naive Bayes.
