Insights on Housing Data: Multiple Factors behind House Price

Ziqiao Liu
Posted on Oct 25, 2016

Motivation

When people desire to own a house of their own ... What do they usually consider?

When was the house built?  House style? Location? Building material?

Are these the features that  affect house prices?  Based on an open dataset published through Kaggle , we explore some insights behind the house pricing.

Data Description

This dataset describes the sale of individual residential property in city Ames, Iowa from Jan 2006  to July 2010, which includes 80 variables(23 nominal, 23 ordinal, 14 discrete, and 20 continuous) for assessing the house sale price. Those variables focus on property quality and quantity, looking at the typical information most potential home buyers consider when making a decision. Although in the original data set, observations with unreasonable values (sales data don’t represent actual market values) have already been removed, general living area with more than 4000 square feet has also been removed from the data set according to the recommendation from paper [1]. Also, data with house sold year at 2010 has been removed since it does not cover information for the whole year. Finally for this  R data visualization project, 8 variables , 1281 observations (containing categorical data and continuous data) are selected from the original dataset, which includes Sale Price ($), House Built Year, House Sold Year, House Sold Month, House Style, House Location Zone, House Foundation and Location Zone.

Data Visualization and Analysis

p1

p2

p22

Scatter plots above show the relationship between house sale prices and the house built year.  The price trend is generally increasing; the newer the building, the higher the price. Different color dots represent different house style categories, which are 1.5 Story, 1.5 Story(U), 1-Story, 2.5 Story, 2.5 Story(U).

For example, 1.5 Story(U) means one and half story with an unfinished story or basement represented by "U".The definition of a half story is the floor area partially or wholly built into the framing of the roof, which is still livable and with a sloping roof , usually having lights from dormer windows.

From the plots above, the house price trend is increasing. The newer the house the higher is the price according to the regression line. Popular house styles are 1.5 Story, 1 Story and 2 Story, which are always needed in house market.   The price range distribution is wide after the year 2000 which means that house prices are  affected by other factors. Moreover, 1.5 Story(U), 2.5 Story and 2.5 Story(U) house style disappeared in the market after the year 1960 and two new house styles (Split Foyer, Split Level) emerged in the housing market with most house prices between $100,000 and $200,000.

The split foyer house style is a 1970s 2- story house design featuring small front entryway between floors, which has two short stairs, one leads up to a main living level and another one goes down to a finished lower level. Many people have complaints about the small entrance of this house style especially in winter time, and maybe this is one of the reasons why it has a lower price compared to Split Level style house, even though both of them are featured as half a story difference in adjacent rooms.

The split level house style is basically a “colonial” style house and could be 3 or 4 levels not just 2. Rooms in the house are somewhat above or below adjacent rooms and the floor levels difference is approximately half a story.

Let’s move on to the house sale history regarding years and months. Plots below show the number of houses  sold in different years.  The median price is marked on the top of the bar.  It would appear as though house prices were  stable from 2006 to 2009. The number of houses sold peaks in July, while the highest prices peak in September.  

 

 

maybe p3

p4

 

Location always matters. The plot below reveals the relationship between house sale price and location zone. Residential High (RH) zone has a stable house price while there is a large variance within the  Residential Low (RL) zone and the  Residential Median (RM) zone.   Floating Village(FV) is a special area where a retirement community was developed and have the highest median price.

The last plot reveals that  people do not ignore house foundation material when purchasing a house. The plot shows the relationship between the overall quality house and the house foundation material. A high-quality house which means the overall quality score above 6 is usually with a Brik & Tile foundation. Slab and Poured Concrete exist in low-quality houses. This information may be helpful for people to estimate the true house price.

p5

p6

Conclusion

Based on above data visualization results, some insights behind home values have been revealed. House built year is one factor in deciding the home value. Season and location play their role in affecting house prices, and a high quality house, based on its foundation material, also affects pricing.  More research could be done on variables like house living area, bathroom numbers, and bedroom numbers related to  house prices to prepare a house price prediction model.

Reference

[1] Dean De Cock , “Ames, Iowa: Alternative to the Boston Housing Data as an End of Semester Regression Project”, Journal of Statistics Education, Volume 19, Number 3(2011).

 

About Author

Leave a Comment

Avatar
masennus February 16, 2017
Great article.

View Posts by Categories


Our Recent Popular Posts


View Posts by Tags

2019 airbnb Alex Baransky alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus API Application artist aws beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep Bundles California Cancer Research capstone Career Career Day citibike clustering Coding Course Demo Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Classes Demo Day Demo Lesson Discount dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Hiring Partners Industry Experts Instructor Blog Instructor Interview Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter lasso regression Lead Data Scienctist Lead Data Scientist leaflet Lectures linear regression Live Chat Live Online Bootcamp Logistic Regression machine learning Maps matplotlib Medical Research Meet the team meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Online Online Bootcamp Online Lectures Online Training Open Data painter pandas Part-time Portfolio Development prediction Prework Programming PwC python python machine learning python scrapy python web scraping python webscraping Python Workshop R R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking Realtime Interaction recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau team TensorFlow Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping Weekend Course What to expect word cloud word2vec XGBoost yelp