House Prices Dataset

Subtitle:

Detailed Real Estate Data for Predicting House Prices and Analyzing Market Trends

Description:

This dataset contains information on 21,613 properties, making it a comprehensive resource for exploring real estate market trends and building predictive models for house prices. The data includes various features capturing property details, location, and market conditions, providing ample opportunities for data exploration, visualization, and machine learning applications.

Key Features:

• General Information:

  • id: Unique identifier for each property.
  • date: Date of sale.

• Price Details:

  • price: Sale price of the house.

• Property Features:

  • bedrooms: Number of bedrooms.
  • bathrooms: Number of bathrooms (including partials as fractions).
  • sqft_living: Living space area in square feet.
  • sqft_lot: Lot size in square feet.
  • floors: Number of floors.
  • waterfront: Whether the property has a waterfront view.
  • view: Quality of the view rating.
  • condition: Overall condition of the house.
  • grade: Grade of construction and design (scale of 1–13).

• Additional Metrics:

  • sqft_above: Square footage of the property above ground.
  • sqft_basement: Basement area in square feet.
  • yr_built: Year the property was built.
  • yr_renovated: Year of last renovation.

• Location Coordinates:

  • zipcode: ZIP code of the property.
  • lat and long: Latitude and longitude coordinates.

• Neighbor Comparisons:

  • sqft_living15: Average living space of 15 nearest properties.
  • sqft_lot15: Average lot size of 15 nearest properties.

Use Cases:

• Predicting house prices using regression models.
• Identifying the impact of various features (e.g., number of bedrooms, location) on property prices.
• Analyzing market trends and spatial distribution of real estate prices.

This dataset is a valuable resource for anyone interested in real estate analytics, machine learning, or geographic data visualization.

Context

The purpose of this dataset is to provide updated data on the Zillow Observed Rent Index (ZORI). Most of the Zillow datasets on Kaggle have not been updated in four years, and no other dataset except one contains information related to rent. Providing updated data on this will also allow the community to analyze the effects of COVID-19 on rent prices, which could not be done with previous available data sets.

Content

Zillow Observed Rent Index (ZORI): A smoothed measure of the typical observed market rate rent across a given region. ZORI is a repeat-rent index that is weighted to the rental housing stock to ensure representativeness across the entire market, not just those homes currently listed for-rent. The index is dollar-denominated by computing the mean of listed rents that fall into the 40th to 60th percentile range for all homes and apartments in a given region, which is once again weighted to reflect the rental housing stock. Details available in ZORI methodology. https://www.zillow.com/research/methodology-zori-repeat-rent-27092/

This dataset contains two files. The Metro dataset looks at the median rent prices for large US cities. The ZIP code dataset breaks the US cities down by their ZIP codes. Note that the region IDs in both datasets are only used for tracking purposes. Also, some of the ZIP codes under the Region Name are less than the standard five-digit zip code and unreliable. Even if you add zeros in accounting for possible formatting mistakes. It is recommended to remove these entries since there is no way to identify which ZIP code the entry actually represents. These entries are left in here in case some analyst can solve the issue.

Acknowledgements

Zillow provides many useful open source datasets that relate to housing, which can be found at Zillow Research Data. https://www.zillow.com/research/data/ This dataset was also prompted by an older dataset I came across that only lacked updated data. https://www.kaggle.com/zillow/rent-index Thumbnail and banner picture is from this pixabay artist https://pixabay.com/users/pexels-2286921/

Inspiration

1. Where are the cheapest and most expensive ZIP codes to live?
2. We all know rent increases overtime, but has it been increasing at a faster rate since 2014?
3. If rent has been increasing at a faster rate, what year did it increase the fastest?
4. What cities or ZIP codes are increasing rent the fastest and by how much?
5. Did rent continue to increase during the COVID-19 pandemic, and was it at a faster or slower rate than previous years?

Rents for industrial real estate in the U.S. have increased since 2017, with flexible/service space reaching the highest price per square foot in 2024. In just a year, the cost of, flex/service space rose by nearly *****U.S. dollars per square foot. Manufacturing facilities, warehouses, and distribution centers had lower rents and experienced milder growth. Los Angeles, Orange County, and Inland Empire, California, are some of the most expensive markets in the country. Office real estate is pricier Industrial real estate is far from being the most expensive commercial property type. For instance, average rental rates in major U.S. metros for office space are much higher than those for industrial space. This is most likely because office units are generally located in urban areas where there is limited space and thus higher demand, whereas industrial units are more suited to the outskirts of such urban areas. Industrial units, such as warehouses or factories, require much more space because they need to house large, heavy equipment or serve as a storage unit for future shipments. Big-box distribution space is gaining in importance Warehouses and distribution may currently command the lowest average rent per square foot among industrial space types, but the growing popularity of the asset class has earned it considerable gains over the past years. In 2021 and 2022, high occupier demand and insufficient supply led to soaring taking rent of big-box buildings. During that time, the vacancy rate of distribution centers fell below ****percent. The development of industrial and logistics facilities has accelerated since then, with the new supply coming to market, causing the vacancy rate to increase and the pressures on rent to ease.

Overview

This residential real estate data set was created by Redfin, an online real estate brokerage. Published on January 9th, 2022, this data summarize the monthly housing market for every State, Metro, and Zip code in the US from 2012 to 2021. Redfin aggregated this data across multiple listing services and has been gracious enough to include property type in their reporting. Please properly cite and link to RedFin if you end up using this data for your research or project.

Source: RedFin Data Center

Property Type

Property type defined by RedFin

• All Residential: All properties defined as single-family, condominium, co-operative, townhouses, and multi-family (2-4 units) homes with a county record.
• Single Family Home (SFH): are homes built on a single lot, with no shared walls. Sometimes there’s a garage, attached or detached.
• Condominium (Condo): Usually a single unit within a larger building or community. Generally come with homeowners’ associations (HOAs), which require the residents to pay monthly or yearly dues.
• Cooperatives (Co-op): Usually a single unit within a larger building or community, but with a different way of holding a title to a shared building. You join a community and everyone in the community owns the building together.
• Townhouse: a hybrid between a condo and a single-family home. They are often multiple floors, with one or two shared walls, and some have a small yard space or rooftop deck. They’re generally larger than a condo, but smaller than a single-family home.
• Multifamily (2-4 units): They are essentially a home that has been turned into two or more units but the units cannot be purchased individually. There is one owner for the whole building.
• Land: Just land, no home of any type for sale.

Source: Building Types

Property Type

For more definitions, please visit RedFin Data Center Metrics

• Average sale to list: The mean ratio of each home's sale price divided by their list price covering all homes with a sale date during a given time period. Excludes properties with a sale price of 50%.
• Home sales: Total number of homes with a sale date during a given time period.
• Inventory: Total number of active listings on the last day of a given time period.
• Median active list ppsf: The median list price per square foot of all active listings.
• Median active list price: The median list price of all active listings.
• Median active listings: The median of how many listings were active on each day within a given time period.
• Median days on market: The number of days between the date the home was listed for sale and when the home went off-market/pending sale covering all homes with an off-market date during a given time period where 50% of the off-market homes sat longer on the market and 50% went off the market faster. Excludes homes that sat on the market for more than 1 year.
• Median days to close: The median number of days a home takes to go from pending to sold.
• Median list price: The most recent listing price covering all homes with a listing date during a given time period where 50% of the active listings were above this price and 50% were below this price.
• Median list price per square foot: The most recent listing price divided by the total square feet of the property (not the lot) covering all homes with a listing date during a given time period where 50% of the active listings were above this price per sqft and 50% were below this price per sqft.
• Median listing with price drops: The median of how many listings were active on each day and whose current list price is less than the original list price within a given time period.
• Median sale price: The final home sale price covering all homes with a sale date during a given time period where 50% of the sales were above this price and 50% were below this price.
• Median sale price per square foot: The final home sale price divided by the total square feet of the property (not the lot) covering all homes with a sale date during a given time period where 50% of the sales were above this price per sqft and 50% were below this price per sqft.
• Months of supply: When data are monthly, it is inventory divided by home sales. This tells you how long it would take supply to be bought up if no new homes came on the market.
• New listings: Total number of homes with a listing added date during a given time period.
• Off market in two weeks: The total number of homes that went under contract within two weeks of their listing date.
• Pending home sales: Total homes that went under contract during the period. Excludes homes that were on the market longer than 90 ...

https://raw.githubusercontent.com/Masterx-AI/Project_Housing_Price_Prediction_/main/hs.jpg" alt="">

Description:

A simple yet challenging project, to predict the housing price based on certain factors like house area, bedrooms, furnished, nearness to mainroad, etc. The dataset is small yet, it's complexity arises due to the fact that it has strong multicollinearity. Can you overcome these obstacles & build a decent predictive model?

Acknowledgement:

Harrison, D. and Rubinfeld, D.L. (1978) Hedonic prices and the demand for clean air. J. Environ. Economics and Management 5, 81–102. Belsley D.A., Kuh, E. and Welsch, R.E. (1980) Regression Diagnostics. Identifying Influential Data and Sources of Collinearity. New York: Wiley.

Objective:

• Understand the Dataset & cleanup (if required).
• Build Regression models to predict the sales w.r.t a single & multiple feature.
• Also evaluate the models & compare thier respective scores like R2, RMSE, etc.

London Property Listings Dataset

Description

This dataset expands upon the original London Property Listings by including additional attributes to facilitate deeper analysis of rental properties in London. It is ideal for research and projects related to real estate trends, price categorization, and area-wise analysis in one of the world's busiest markets.

Dataset Features

• Price: Monthly rental price in GBP.
• Property Type: Classification of the property (e.g., Apartment, Flat).
• Bedrooms: Number of bedrooms in the property.
• Bathrooms: Number of bathrooms.
• Size: Property size in square feet (where available).
• Postcode: Postal code of the property location.
• Area: General area or neighborhood information.
• Price_Category: Categorization of prices into predefined ranges (e.g., Low, Medium, High).
• Area_Avg_Price: Average price of properties within the same area.

Potential Use Cases

• Price Analysis: Study how property attributes impact rental prices.
• Price Prediction Models: Utilize the dataset for machine learning tasks like regression and classification.
• Regional Insights: Compare rental trends across different neighborhoods.
• Categorical Analysis: Investigate trends within predefined price categories.

Data Summary

• Total Records: 29,537
• Total Attributes: 9
• Data Completeness: No missing values. All columns are fully populated.

Attribution

This dataset was prepared and uploaded by Mehmet Emre Sezer. It is intended for educational and non-commercial use.

Data, statistics and adopted local options related to property taxes

Context

Zillow operates an industry-leading economics and analytics bureau led by Zillow’s Chief Economist, Dr. Stan Humphries. At Zillow, Dr. Humphries and his team of economists and data analysts produce extensive housing data and analysis covering more than 500 markets nationwide. Zillow Research produces various real estate, rental and mortgage-related metrics and publishes unique analyses on current topics and trends affecting the housing market.

At Zillow’s core is our living database of more than 100 million U.S. homes, featuring both public and user-generated information including number of bedrooms and bathrooms, tax assessments, home sales and listing data of homes for sale and for rent. This data allows us to calculate, among other indicators, the Zestimate, a highly accurate, automated, estimated value of almost every home in the country as well as the Zillow Home Value Index and Zillow Rent Index, leading measures of median home values and rents.

Content

The Zillow Rent Index is the median estimated monthly rental price for a given area, and covers multifamily, single family, condominium, and cooperative homes in Zillow’s database, regardless of whether they are currently listed for rent. It is expressed in dollars and is seasonally adjusted. The Zillow Rent Index is published at the national, state, metro, county, city, neighborhood, and zip code levels.

Zillow produces rent estimates (Rent Zestimates) based on proprietary statistical and machine learning models. Within each county or state, the models observe recent rental listings and learn the relative contribution of various home attributes in predicting prevailing rents. These home attributes include physical facts about the home, prior sale transactions, tax assessment information and geographic location as well as the estimated market value of the home (Zestimate). Based on the patterns learned, these models estimate rental prices on all homes, including those not presently for rent. Because of the availability of Zillow rental listing data used to train the models, Rent Zestimates are only available back to November 2010; therefore, each ZRI time series starts on the same date.

Acknowledgements

The rent index data was calculated from Zillow's proprietary Rent Zestimates and published on its website.

Inspiration

What city has the highest and lowest rental prices in the country? Which metropolitan area is the most expensive to live in? Where have rental prices increased in the past five years and where have they remained the same? What city or state has the lowest cost per square foot?