House Prices Advanced Regression Techniques

The work performed here is based on data from the Kaggle competition below:
https://www.kaggle.com/competitions/house-prices-advanced-regression-techniques

Business Problem

From the perspective of an online real estate market company, there are two challenges:

• Accurately assess home values by neighborhood
• Determine importance of various attributes in determining that value

Developing a data-driven / model-based approach can potentially:

• Provide more precision in valuation methodology
• Assess what factors drive the overall value of a home

Background Research

Zillow

Zillow is an online real estate marketplace company.

Zillow is famous for using state of the art statistical and machine learning models to produce Zestimates (their trademarked valuation model).

To calculate a Zestimate, Zillow uses a sophisticated neural network-based model that incorporates data from the following sources:

• Market trends
• On-market data
• Off-market data
• Home characteristics
• County and tax assessor records
• Direct feeds from listing services and brokerages

https://www.zillow.com/research/zestimate-forecast-methodology/

Opendoor

Opendoor is an online real estate marketplace company. According to an article written by the company, there are * primary factors that influence home value:

• Location
• Interest rates
• The local market
• Age and condition
• Economic indicators
• Neighborhood comps
• Upgrades and updates
• Home size and usable space

https://www.opendoor.com/w/blog/factors-that-influence-home-value

Inference Problem

X: 79 explanatory variables describing aspects of residential homes in Ames, Iowa y: Home price

Develop a model to predict home price based on a collection of attributes about the home and surrounding neighborhood.

Exploratory data analysis

Feature engineering

Model selection

Model evaluation