The below dataset shows the top 800 biggest cities in the world and their populations in the year 2024. It also tells us which country and continent each city is in, and their rank based on population size. Here are the top ten cities:

• Tokyo, Japan - in Asia, with 37,115,035 people.
• Delhi, India - in Asia, with 33,807,403 people.
• Shanghai, China - in Asia, with 29,867,918 people.
• Dhaka, Bangladesh - in Asia, with 23,935,652 people.
• Sao Paulo, Brazil - in South America, with 22,806,704 people.
• Cairo, Egypt - in Africa, with 22,623,874 people.
• Mexico City, Mexico - in North America, with 22,505,315 people.
• Beijing, China - in Asia, with 22,189,082 people.
• Mumbai, India - in Asia, with 21,673,149 people.
• Osaka, Japan - in Asia, with 18,967,459 people.

Introduction

The primary purpose for this dataset was to build a regression model to accurately predict housing prices in Japan.

• Which features are the most important in predicting housing prices?
• Can you think of other features that may be important that can be derived from this dataset?

Supplementary Code and Notebooks

An example notebook for regression analysis , the raw dataset and the cleaning scripts can be found at the following repo:

https://github.com/bmcgloughlin71/Japanese_future_real_estate_prices/tree/main

Housing Price Data Column Descriptions

Name	Description	Notes
Type	A tag distinguishing whether real estate is land only or land with a building	Since this data set is only focusing on building prices this tag is redundant but useful for filtering with the script referenced above
Prefecture	Which of the 47 prefectures the property is located
Location	Which town, village or city within the prefecture the property is located
TotalTransactionValue	The total transaction value of the property	in yen (¥)
Area	Total area of the property (land included)	in square meters (m²)
Frontage	Length of land at the forefront of the property	in meters (m)
TotalFloorArea	Total area of the property footprint	in square meters (m²)
ConstructionYear	Year of construction (not necessarily the year of transaction)
BuildingCoverageRatio	What percentage of the land is covered by the property	in percentage points (%)
FloorAreaRatio	Total floor area of all floors to land area ratio	in percentage points (%). Somewhat counterintuitively this may be more than 100%
Quarter	Which quarter of the year the property was sold	1 = first quarter, 2 = second quarter etc.
Year	Year of purchase
RegionCommercialArea	In a commercial Area?	Boolean
RegionIndustrialArea	In an industrial Area?	Boolean
RegionPotentialResidentialArea	In a potential residential Area?	Boolean
RegionResidentialArea	In a residential Area?	Boolean
MunicipalityCategory	Is the property in a village, town, city or prefecture capital city ?	1 = village, 2 = town, 3 = city, 4 = capital city
Region_Chubu	In Chubu?	Boolean
AverageTimeToStation	Average walking time to the nearest station	in minutes
FloorAreaGreaterFLag	Is the floor area greater than 2000 m² ?	Boolean
BeforeWarFlag	Was the building built before the World War 2?	Boolean
frontage_greater_than_50	Is the frontage length greater than 50 m?	Boolean
AreaGreaterFlag	Is the total area greater than 2000 m² ?	Boolean
Region_Chugoku	In Chugoku?	Boolean
Region_Hokkaido	In Hokkaido?	Boolean
Region_Kansai	In Kansai?	Boolean
Region_Kanto	In Kanto?	Boolean
Region_Kyushu	In Kyushu?	Boolean
Region_Shikoku	In Shikoku?	Boolean
Region_Tohoku	In Tohoku?	Boolean
City,Town,Ward,Village code	Postcode
Migration	Number of people who moved to the property's location	Based on migration data from the year before the sale, or from 2008 if the sale occurred in 2009 or earlier

Location Data Column Descriptions

Name	Description	Notes
latitude	geographical latitude	In degrees (decimal)
longitude	geographical longitude	In degrees (decimal)
Distance_to_designated_city	Distance to nearest designated city in kilometers	Includes Tokyo
Nearest_designated_city	The nearest designated city	Includes Tokyo
Close_to_Tokyo	True if Tokyo is closer than any other designated city	Boolean
Close_to_greater_Tokyo_area	True if the nearest designated city is in the greater Tokyo area, namely Yokohama, Kawasaki, Saitama, Chiba or Sagamihara	Boolean
Close_to_designated_city_flag	True if area is within 5km of either Tokyo or any other designated city	Boolean

Acknowledgments

This data set is an extension but not quite identical to:

https://www.kaggle.com/datasets/nishiodens/japan-real-estate-transaction-prices

Unemployment Rate in Japan remained unchanged at 2.60 percent in October. This dataset provides the latest reported value for - Japan Unemployment Rate - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news.

Employment Rate in Japan increased to 62.50 percent in September from 62.30 percent in August of 2025. This dataset provides - Japan Employment Rate- actual values, historical data, forecast, chart, statistics, economic calendar and news.

Housing Index in Japan increased to 140.54 points in September from 137.89 points in August of 2025. This dataset provides - Japan Construction Starts - actual values, historical data, forecast, chart, statistics, economic calendar and news.