Quarterly median house prices for metropolitan Adelaide by suburb

Moulden in Greater Darwin, Northern Territory was the most affordable capital city housing suburb in Australia as of November 2024, with a median property value of around ******* Australian dollars. The Gray suburb, also in Greater Darwin, was the second-most affordable capital city housing suburb.

In June 2025, a single-family house in Oak Bay cost **** million Canadian dollars. Oak Bay was the most expensive suburb in Victoria, British Columbia, followed by Highlands and North Saanich. Victoria: an overview Victoria is the capital city of the province of British Columbia. The city is located south of Vancouver, and across the U.S. border from Seattle. In 2020, the average home price in Victoria was ****million Canadian dollars, which placed the city as the sixth most expensive Canadian city for residential real estate. Home affordability in Canada Housing affordability is, undoubtedly, one of the biggest barriers to homeownership in Canada. In 2025, the ratio of homeownership costs to income was **** percent. Nevertheless, more expensive locations in the country had a higher ratio, with Vancouver exceeding ** percent, suggesting that on average, mortgage payments were slightly lower than the average income.

Urban housing location and locational amenities play an important role in median house price distribution and growth among the suburbs of many metropolitan cities in developed countries, such as Australia. In particular, distance from the central business district (CBD) and access to the transport network plays a vital role in house price distribution and growth over various suburbs in a city. However, Australian metropolitan cities have experienced increases in housing prices by up to 120% over the last 20 years, and the growth pattern was different across all suburbs in a city, such as in Melbourne. Therefore, this study examines the impacts of locational amenities on house price changes across various suburbs in Melbourne over the three census periods of 2006, 2011, and 2016, and suggests some strategic guidelines to improve the availability and accessibility of locational amenities in the suburbs with less concentrated amenities.

This study chose three Local Government Areas (LGAs) of Maribyrnong, Brimbank and Wyndham in Melbourne. Each LGA has been selected as a case study because many low-income people live in these LGAs’ areas. Further, some suburbs of these LGAs have maintained similar housing prices for an extended time, while some have not.

The study applied a quantitative spatial methodology to examine the housing price distribution and growth patterns by evaluating the concentration and accessibility of locational urban amenities using GIS-based techniques and a spatial data set. The spatial data analyses were performed by spatial statistics methods to measure central tendency, Local Moran’s I of LISA clustering, Kernel Density Estimation (KDE), Kernel Density Smoothing (KDS). These tests were used to find the patterns of house price distribution and growth. The study also identified the accessibility of amenities in relation to median house price distribution and growth. Spatial Autoregressive Regression (SAR), Spatial Lag, and Spatial Errors models were used to identify the spatial dependencies to test the statistical significance between the median house price and the concentration and access of local urban amenities over the three census years.

This study found three median house price distribution and growth patterns among the suburbs in the three selected LGAs. There are growth differences in the median house price for different census years between 2006 and 2011, 2011 and 2016, and 2006 and 2016. The Low-High (LH) median house price distribution clusters between 2006 and 2011 became High-High (HH) clusters between the census years 2011 and 2016, and 2006 and 2016. The median house price growth rate increased significantly in the census years between 2006 and 2011. Most of the HH median house price distribution and growth clusters’ tendencies were closer to the Melbourne CBD. On the other hand, the Low-Low (LL) distribution and growth clusters were closer to Melbourne’s periphery. The suburbs located further away had low access to amenities. The HH median house price clusters are located closer to stations and educational institutes. Better access to locational amenities led to more significant HH median house price clusters, as the median house price increased at an increasing rate between 2011 and 2016. The HH median house price clusters recorded more growth between 2006 and 2016. The suburbs with train stations had better access to most other locational amenities. Almost all HH median house price clusters had train stations with higher access to amenities.

There was a consistent relationship between median house price distribution, growth patterns, and locational urban amenities. The spatial lag and spatial error model tests showed that between 2006 and 2011, and 2006 and 2016, there were differences in the amenities. Still, these did not affect the outcomes in observations, and were related only to immeasurable factors for some reason. Therefore, the higher house price in the neighbouring suburb could increase the price in that suburb. The research also found from the regression analysis that highly significant amenities confirming travel time to the CBD by bus, and distance to the CBD, were negatively related in all three previous census years. This negative relationship estimates that the house price growth is lower when the distance is longer. Due to this travel to the CBD by bus is not a popular option for households. The train stations are essential for high house price growth. The house price growth is low when homes are further away from train stations and workplaces.

This thesis has three contributions. Firstly, it uses the Rational Choice Theory (RCT), providing a theoretical basis for analysing households’ mutually interdependent preferences of urban amenities that are found to regulate house price growth clusters. Secondly, the methodological contribution uses the GIS-defined cluster mapping and spatial statistics in queries and reasoning, measurements, transformations, descriptive summaries, optimisation, and hypothesis testing models between house price distribution and growth, and access to urban locational amenities. Thirdly, this research contributes to designing practical guidelines to identify local urban amenities for planning local area development.

Overall, this thesis demonstrates that the median house price distribution and growth patterns are highly correlated with the concentration and accessibility of locational urban amenities among the suburbs in three selected LGAs in Melbourne over the three census years (i.e., 2006, 2011, and 2016). The findings bring to the fore the need for research at the local and state levels to identify specific amenities relevant to the middle-class house distribution strategy, which can be helpful for investors, estate agents, town planners, and builders as partners for effective local development. The future study might use social, psychological, and macroeconomic variables not considered or used in this research.

A dataset comprising the price, address, number of bathrooms, number of bedrooms, city, and province of real estate listings for Canada's top 45 most populous cities, according to the 2021 census.

Variables:

1. City: City or major metropolitan area within which listings were found. For example, Toronto may include listings from surrounding suburbs such as Markham, Oakville, etc.
2. Price: Listed price for the property in Canadian dollars.
3. Address: Street address and, where applicable, unit number for the listing.
4. Number_Beds: Number of bedrooms mentioned in the listing.
5. Number_Baths: Number of bathrooms mentioned in the listing.
6. Province: Province in which each city resides. Note, border towns such as Ottawa do not include listings from the surrounding out-of-province cities like Gatineau.
7. Population: City population. According to simplemaps (https://simplemaps.com/data/canada-cities)
8. Longitude / Latitude: Longitude and Latitude data for individual cities, taken from simpelmaps (https://simplemaps.com/data/canada-cities)
9. Median_Family_Income: Median household income for the city taken from the 2021 Canadian census.

This dataset can be used for basic linear regression problems or for basic exploratory data analysis.

Data is currently representative of prices as of October 29th 2023. Future updates will occur monthly.

The average resale house price in Canada was forecast to reach nearly ******* Canadian dollars in 2026, according to a January forecast. In 2024, house prices increased after falling for the first time since 2019. One of the reasons for the price correction was the notable drop in transaction activity. Housing transactions picked up in 2024 and are expected to continue to grow until 2026. British Columbia, which is the most expensive province for housing, is projected to see the average house price reach *** million Canadian dollars in 2026. Affordability in Vancouver Vancouver is the most populous city in British Columbia and is also infamously expensive for housing. In 2023, the city topped the ranking for least affordable housing market in Canada, with the average homeownership cost outweighing the average household income. There are a multitude of reasons for this, but most residents believe that foreigners investing in the market cause the high housing prices. Victoria housing market The capital of British Columbia is Victoria, where housing prices are also very high. The price of a single family home in Victoria's most expensive suburb, Oak Bay was *** million Canadian dollars in 2024.

• Objective: To predict the prices of houses in the City of Melbourne
• Approach: Using Decision Tree and Random Forest https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10868729%2Ffc6fb7d0bd8e854daf7a6f033937a397%2FPicture1.png?generation=1693489996707941&alt=media" alt="">
• Data Cleaning:
• Date column is shown as a character vector which is converted into a date vector using the library ‘lubridate’
• We create a new column called age to understand the age of the house as it can be a factor in the pricing of the house. We extract the year from column ‘Date’ and subtract it from the column ‘Year Built’
• We remove 11566 records which have missing values
• We drop columns which are not significant such as ‘X’, ‘suburb’, ‘address’, (we have kept zipcode as it serves the purpose in place of suburb and address), ‘type’, ‘method’, ‘SellerG’, ‘date’, ‘Car’, ‘year built’, ‘Council Area’, ‘Region Name’
• We split the data into ‘train’ and ‘test’ in 80/20 ratio using the sample function
• Run libraries ‘rpart’, ‘rpart.plot’, ‘rattle’, ‘RcolorBrewer’
• Run decision tree using the rpart function. ‘Price’ is the dependent variable https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10868729%2F6065322d19b1376c4a341a4f22933a51%2FPicture2.png?generation=1693490067579017&alt=media" alt="">
• Average price for 5464 houses is $1084349
• Where building area is less than 200.5, the average price for 4582 houses is $931445. Where building area is less than 200.5 & age of the building is less than 67.5 years, the avg price for 3385 houses is $799299.6.
• $4801538 is the Highest average prices of 13 houses where distance is lower than 5.35 & building are is >280.5
  https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10868729%2F136542b7afb6f03c1890bae9b07dc464%2FDecision%20Tree%20Plot.jpeg?generation=1693490124083168&alt=media" alt="">
• We use the caret package for tuning the parameter and the optimal complexity parameter found is 0.01 with RMSE 445197.9 https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10868729%2Feb1633df9dd61ba3a51574873b055fd0%2FPicture3.png?generation=1693490163033658&alt=media" alt="">
• We use library (Metrics) to find out the RMSE ($392107), MAPE (0.297) which means an accuracy of 99.70% and MAE ($272015.4)
• Variables ‘postcode’, longitude and building are the most important variables
• Test$Price indicates the actual price and test$predicted indicates the predicted price for particular 6 houses. https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10868729%2F620b1aad968c9aee169d0e7371bf3818%2FPicture4.png?generation=1693490211728176&alt=media" alt="">
• We use the default parameters of random forest on the train data https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10868729%2Fe9a3c3f8776ee055e4a1bb92d782e19c%2FPicture5.png?generation=1693490244695668&alt=media" alt="">
• The below image indicates that ‘Building Area’, ‘Age of the house’ and ‘Distance’ are the most important variables that affect the price of the house. https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10868729%2Fc14d6266184db8f30290c528d72b9f6b%2FRandom%20Forest%20Variables%20Importance.jpeg?generation=1693490284920037&alt=media" alt="">
• Based on the default parameters, RMSE is $250426.2, MAPE is 0.147 (accuracy is 99.853%) and MAE is $151657.7
• Error starts to remain constant between 100 to 200 trees and thereafter there is almost minimal reduction. We can choose N tree=200. https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10868729%2F365f9e8587d3a65805330889d22f9e60%2FNtree%20Plot.jpeg?generation=1693490308734539&alt=media" alt="">
• We tune the model and find mtry = 3 has the lowest out of bag error
• We use the caret package and use 5 fold cross validation technique
• RMSE is $252216.10 , MAPE is 0.146 (accuracy is 99.854%) , MAE is $151669.4
• We can conclude that Random Forest give us more accurate results as compared to Decision Tree
• In Random Forest , the default parameters (N tree = 500) give us lower RMSE and MAPE as compared to N tree = 200. So we can proceed with those parameters.

Housing Index in the United States decreased to 435.40 points in September from 435.60 points in August of 2025. This dataset provides the latest reported value for - United States House Price Index MoM Change - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news.

1) Data Introduction • The Real Estate DataSet consists of 506 examples, including home prices in the Boston suburbs and various residential and environmental characteristics.

2) Data Utilization (1) Real Estate DataSet has characteristics that: • The dataset provides 13 continuous variables and one binary variable, including crime rate, house size, environmental pollution, accessibility, tax rate, and population characteristics. (2) Real Estate DataSet can be used to: • House Price Forecast: It can be used to develop a regression model that predicts the median price (MEDV) of a house based on various residential and environmental factors. • Analysis of Urban Planning and Policy: It can be used for urban development and policy making by analyzing the impact of residential environmental factors such as crime rates, environmental pollution, and educational environment on housing values.

The price of residential property in New Zealand was the highest in the Auckland region in October 2025, with an average sale price of over *** million New Zealand dollars. The most populated city in the country, Auckland, has consistently reported higher house prices compared to most other regions. Buying property in New Zealand, particularly in its major cities, is expensive. The nation has one of the highest house-price-to-income ratios in the world. Auckland residential market The residential housing market in Auckland is competitive. Prices have been slowly decreasing although the Auckland region experienced an annual increase in the average residential house price in October 2025 compared to the same month in the previous year. The price of residential property in Auckland was the highest in the Auckland City district, with an average sale price of around **** million New Zealand dollars. Home financing Due to the rising cost of real estate, an increasing number of New Zealanders who want to own their own property are taking on mortgages. Most residential mortgage lending in New Zealand went to owner-occupier borrowers, followed by first home buyers. In addition to mortgage lending, previously under the KiwiSaver HomeStart initiative, first-home buyers in New Zealand were able to apply to withdraw all or part of their KiwiSaver retirement savings to assist with purchasing a first home. Nonetheless, the scheme was discontinued in May 2024. Furthermore, even with a large initial deposit, it may take decades for many borrowers to pay off their mortgage.

The report lists the percentage shift in median prices between quarters as well as the change over a 12-month period. An overall Melbourne metropolitan median sale price and country Victoria median sale price are also included for each property type.

The Boston Housing dataset, which is often used for regression analysis and predictive modeling tasks, doesn't typically have an official "subtitle." However, it's commonly referred to as the "Boston Housing dataset" or the "Boston Housing Price dataset" due to its focus on housing-related features and its primary target variable being the median value of owner-occupied homes in Boston suburbs.

Column Description

Columns: 1. CRIM: per capita crime rate by town (numeric) 2. ZN: proportion of residential land zoned for lots over 25,000 sq.ft. (numeric) 3. INDUS: proportion of non-retail business acres per town (numeric) 4. CHAS: Charles River dummy variable (1 if tract bounds river; 0 otherwise) (categorical) 5. NOX: nitric oxides concentration (parts per 10 million) (numeric) 6. RM: average number of rooms per dwelling (numeric) 7. AGE: proportion of owner-occupied units built prior to 1940 (numeric) 8. DIS: weighted distances to five Boston employment centres (numeric) 9. RAD: index of accessibility to radial highways (numeric) 10. TAX: full-value property-tax rate per $10,000 (numeric) 11. PTRATIO: pupil-teacher ratio by town (numeric) 12. B: 1000(Bk - 0.63)^2 where Bk is the proportion of [people of African American descent] by town (numeric) 13. LSTAT: % lower status of the population (numeric) 14. MEDV: Median value of owner-occupied homes in $1000s (target variable) (numeric)

The Coober Pedy area was the most affordable housing suburb in South Australia as of March 2025, with a median property value of around ****** Australian dollars. The Port Pirie West suburb had the next lowest prices for housing, at around ******* dollars.

This is the Boston Housing Dataset, copied from: https://www.kaggle.com/datasets/vikrishnan/boston-house-prices

Each record in the database describes a Boston suburb or town. The data was drawn from the Boston Standard Metropolitan Statistical Area (SMSA) in 1970. The attributes are defined as follows (taken from the UCI Machine Learning Repository1): CRIM: per capita crime rate by town

CRIM per capita crime rate by town ZN proportion of residential land zoned for lots over 25,000 sq.ft. INDUS proportion of non-retail business acres per town CHAS Charles River dummy variable (= 1 if tract bounds river; 0 otherwise) NOX nitric oxides concentration (parts per 10 million) RM average number of rooms per dwelling AGE proportion of owner-occupied units built prior to 1940 DIS weighted distances to five Boston employment centres RAD index of accessibility to radial highways TAX full-value property-tax rate per 10 000 USD PTRATIO pupil-teacher ratio by town B 1000 (Bk - 0.63)^2 where Bk is the proportion of black people by town LSTAT % lower status of the population MEDV Median value of owner-occupied homes in $1000's Missing values: None

Duplicate entries: None

This is a copy of UCI ML housing dataset. https://archive.ics.uci.edu/ml/machine-learning-databases/housing/

It has then been amended to include multiple different correlations:

Directly Derived Features - New features created by applying direct transformations to existing features. For example a scaled version of another (e.g., CRIM_dup_2 = CRIM * 2), or adding some noise to an existing feature (e.g., RM_noisy = RM + random_noise).

Linear Combinations - Combining existing features linearly. For instance, a feature that is a weighted sum of several other features (e.g., weighted_feature = 0.5 * CRIM + 0.3 * NOX + 0.2 * RM).

Polynomial Features - Creating polynomial transformations of existing features. For example, square or cube a feature (e.g., AGE_squared = AGE^2). These will have a predictable correlation with their original feature.

Interaction Terms - Generating features that are the product of two existing features. Revealing interactions between variables (e.g., TAX_RAD_interaction = TAX * RAD).

Duplicate Features with Variations: Duplicate some existing features and add small variations. For example, copy a feature and add a random small value to each entry (e.g., LSTAT_varied = LSTAT + small_random_value).

These have been done by taking the dataset in python and transforming it, for example:

``import pandas as pd import random import numpy as np

List of original column names

original_columns = ["CRIM", "ZN", "INDUS", "CHAS", "NOX", "RM", "AGE", "DIS", "RAD", "TAX", "PTRATIO", "B", "LSTAT"]

Generate features

for col_name in original_columns: # Linear Combinations other_cols = random.sample([c for c in original_columns if c != col_name], 2) df[f"{col_name}_linear_combo"] = 0.5 * df[col_name] + 0.3 * df[other_cols[0]] + 0.2 * df[other_cols[1]]

# Polynomial Features
df[f"{col_name}_squared"] = df[col_name] ** 2

# Interaction Terms
other_col = random.choice([c for c in original_columns if c != col_name])
df[f"{col_name}_{other_col}_interaction"] = df[col_name] * df[other_col]

# Duplicate Features with Variations
df[f"{col_name}_varied"] = df[col_name] + (np.random.rand(df.shape[0]) * 0.05)

Display the DataFrame

print(df) ``

In 2022, the capital city suburb with the strongest ** month growth in housing values was Davoren Park, South Australia, with an annual growth in median property value of **** percent. Elizabeth Grove, another South Australian suburb, also witnessed a large growth in property values with an annual change of **** percent recorded that same year.

This dataset outlines the percent changes in median Estimated Market Values, Aggregate Estimated Market Values, and Parcel Counts by Jurisdiction and Location (City of Saint Paul and suburbs) from 2020 to 2021.

Overview

This dataset is a cleaned and updated version of the classic Boston Housing Dataset, originally made available by the U.S. Census and later popularized in machine learning communities. It contains detailed information about housing prices in Boston suburbs, along with environmental, structural, and socio-economic indicators for each neighborhood.

The dataset is widely used as a benchmark for regression tasks and offers an excellent opportunity to explore linear modeling, feature engineering, multicollinearity analysis, bias mitigation, and more. 📚 Context

Originally published by Harrison and Rubinfeld in 1978, this dataset has been widely adopted in the machine learning and statistics communities. It contains 506 observations, each representing a town or neighborhood in the Boston metropolitan area.

However, some features in the dataset—particularly the B column which encodes race-based information—have become the subject of ethical scrutiny in recent years. Therefore, this version may have undergone data cleaning, feature selection, or modification to ensure it is more appropriate for modern and ethical ML applications. 📊 Features Feature Description CRIM Per capita crime rate by town ZN Proportion of residential land zoned for lots over 25,000 sq. ft. INDUS Proportion of non-retail business acres per town CHAS Charles River dummy variable (= 1 if tract bounds river; 0 otherwise) NOX Nitric oxides concentration (parts per 10 million) RM Average number of rooms per dwelling AGE Proportion of owner-occupied units built before 1940 DIS Weighted distance to five Boston employment centers RAD Index of accessibility to radial highways TAX Property tax rate per $10,000 PTRATIO Pupil-teacher ratio by town B 1000(Bk - 0.63)^2 where Bk is the proportion of Black residents LSTAT Percentage of lower-status population MEDV Median value of owner-occupied homes in $1000s (Target Variable)

🟡 Note: Some features (e.g., CHAS, B, or RAD) may have been removed or modified in this version depending on your ethical preprocessing or cleaning steps.

🎯 Target Variable

MEDV: Median value of owner-occupied homes (in $1000s). This is the value we aim to predict in regression tasks.

✅ Use Cases

This dataset is ideal for:

Predictive modeling using linear regression or advanced ML techniques

Feature engineering and feature selection

Studying the effects of urban and environmental variables on real estate prices

Analyzing multicollinearity and variable importance

Exploring ethical considerations in machine learning

⚖️ Ethical Considerations

The original dataset includes the feature B, which encodes racial information. While historically included for statistical analysis, modern ML best practices recommend caution when using such data to avoid unintended bias or discrimination.

In this version, you may choose to remove or retain the column depending on the intended use and audience.

Always consider the fairness, accountability, and transparency of your ML models.

📁 File Information

Filename: boston_housing_cleaned.csv

Records: 506 rows (observations)

Columns: 13 features + 1 target variable (depending on cleaning)

Missing Values: None (in original); NA if introduced during preprocessing

Source: Based on U.S. Census data (original), sourced from Kaggle and cleaned

📌 Tags

housing-prices · regression · real-estate · data-cleaning · ethical-ml · boston · exploratory-data-analysis · feature-engineering

Median property valuation data for freehold residential properties for 2012 and 2015 at suburb level.

This dataset outlines the median estimated market value of residential properties in the city of Saint Paul and surrounding suburbs.

In 2022, the price for new residential property in Shanghai's inner ring dropped by more than ***** yuan per square meter, to ******* yuan per square meter. Although the local authorities introduced policies to stabilize the market, the real estate market in Shanghai’s central districts remained under downward pressure, similar to those experienced by other major cities in China. The most competitive real estate market in the country Home prices in Shanghai are among the most expensive globally. The area within the city's inner ring road is certainly one of the most competitive real estate markets in all of China, with property prices nearly *********** higher than those outside the outer ring road. Rising prices are far beyond the reach of ordinary residents, and the few who can afford to buy often have to take out substantial mortgages for their homes, resulting in a high proportion of real estate in their personal assets. Challenges facing China’s real estate sector The high level of indebtedness of the Chinese people and the bubbles in the country's real estate sector have become one of the major risks to China's economy. While developers expanded through continuous borrowing and the sale of off-plan properties to homebuyers, the market saw a significant excess of housing supply in most regions. There have also been instances in recent years where developers have had difficulties in completing construction projects or in repaying their loans or bonds. Addressing the risks in China's real estate sector, particularly in companies such as the Evergrande Group and Country Garden, has become an urgent task to ensure China's economic stability and prosperity.