Dark Mode
Amsterdam Property Prediction Dataset
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset aims to assist in predicting residential sales prices in Amsterdam and provides opportunities for practicing feature engineering. It supports a data-driven approach for individuals making significant decisions, such as buying a house, by helping to identify optimal solutions. The data addresses the nuance that asking prices may not directly reflect actual sold prices. A key metric for success involves identifying a house as a good option if its price is economical compared to other listings within the same area.
Columns
- Address: This column details the residential address of each listing. There are 919 unique addresses across 924 entries.
- Zip: This represents the residential postcode for each property. The dataset includes 834 unique postcode values.
- Price: This column indicates the residential price in Euros. The data features 227 unique price points, with 375,000 Euros being the most common price, appearing in 5% of the listings.
- Area: This column specifies the residential area in square metres. The values range from 21 to 623 square metres, with a mean area of 96 square metres and a standard deviation of 57.4.
- Room: This denotes the number of rooms present at the residence. The room count ranges from 1 to 14, with an average of 3.57 rooms and a standard deviation of 1.59.
- Lon: This provides the longitude coordinates for each property. Longitude values span from 4.64 to 5.03, with a mean of 4.89 and a standard deviation of 0.05.
- Lat: This indicates the latitude coordinates for each listing. Latitude values range from 52.3 to 52.4, with a mean of 52.4 and a standard deviation of 0.02.
Distribution
The dataset is provided in CSV format and has a file size of 74.3 kB. It consists of 924 rows and 8 columns. All data points are valid, with no mismatched or missing values across any of the included columns.
Usage
This dataset is ideally suited for:
- Developing and evaluating models for predicting residential sales prices.
- Engaging in feature engineering exercises to enhance model performance.
- Facilitating data-driven decision-making for property purchases.
- Identifying properties that offer better value compared to other listings in a particular area.
- Training and testing machine learning algorithms such as Linear Regression and XGBoost.
Coverage
The data pertains to residential properties located in Amsterdam. It represents a snapshot captured in August 2021. Geographical coordinates for each listing were sourced through the Mapbox API.
License
CC0: Public Domain
Who Can Use It
- Data Scientists and Machine Learning Enthusiasts: To build and refine predictive models for house prices and to practise feature engineering.
- Prospective Home Buyers: To inform their purchasing decisions with data, helping them to find properties that offer good value.
- Real Estate Analysts: To analyse the Amsterdam housing market and understand pricing dynamics.
Dataset Name Suggestions
- Amsterdam Residential Price Data 2021
- August 2021 Amsterdam Housing Prices
- Amsterdam Property Prediction Dataset
- Real Estate Amsterdam Sales Forecast
Attributes
Original Data Source: Amsterdam Property Prediction Dataset
QUALITY