Dark Mode
eBay Germany Auto Sales Data
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This compilation contains detailed records of private used car listings scraped from the German online marketplace, eBay Kleinanzeigen, during 2016. The data provides crucial insights into the German secondary auto market, including pricing trends, vehicle characteristics, power specifications, and geographical distribution. It serves as an excellent resource for market analysis, building machine learning models for price prediction, and practicing data cleaning and preparation techniques. The information covers over 37,000 distinct listings.
Columns
- date_crawled: The specific date when the advertisement was first collected by the scraper.
- name: The descriptive name given to the car in the listing.
- price_EUR: The advertised price for the car, denominated in Euros (EUR).
- ab_test: Indicates whether the listing was included as part of an A/B test campaign.
- vehicle_type: Categorisation of the type of vehicle (e.g., limousine, station wagon).
- registration_year: The year the vehicle was first registered.
- transmission: The mechanism of transmission (e.g., manual or automatic).
- power_ps: The car's power measured in PS (PferdStarke, similar to horsepower).
- model: The specific model name of the car.
- odometer_km: The approximate total kilometres the car has been driven.
- registration_month: The month the car was initially registered.
- fuel_type: The type of fuel the vehicle uses.
- brand: The manufacturer of the car (e.g., Volkswagen, BMW).
- unrepaired_damage: A flag indicating if the car has existing damage that has not yet been fixed.
- date_created: The date when the specific eBay listing was initially created.
- postal_code: The German postal code corresponding to the vehicle's location.
- last_seen_online: The final date the crawler observed the advertisement still active online.
Distribution
The data structure consists of seventeen columns describing various attributes of used cars. There are over 37 thousand records, with approximately 37,900 valid entries across all fields. The data is available in a clean format, typically CSV (
autos_random_50k_cleaned.csv), and has a file size of approximately 6.36 MB. No records exhibit missing or mismatched values. The price ranges significantly, starting near 500 EUR and extending up to 820,000 EUR.Usage
This dataset is ideal for developing machine learning models aimed at predicting used car prices based on features like registration year, mileage, power, and brand. It is also excellent for conducting market research to understand consumer preferences, regional pricing variations across Germany, and the distribution of vehicle types and transmission methods (e.g., 75% manual transmission). Furthermore, it provides valuable practice material for data analytics, particularly for tasks involving cleaning, transforming, and visualising time-series data related to listing creation and crawling dates.
Coverage
Geographic Scope: The coverage is focused exclusively on Germany, identified through the source marketplace (eBay Kleinanzeigen) and the use of German postal codes.
Time Range: The car listings themselves were actively crawled between 5 March 2016 and 7 April 2016. However, the registration years of the vehicles span a far greater historical period, ranging from 1929 up to 2016. Listing creation dates start as early as November 2015.
Vehicle Demographics: The data primarily reflects private sellers offering a wide array of brands, with Volkswagen and BMW being the most frequently listed. Vehicle types vary, with 'limousine' being the most frequent category.
License
CC0: Public Domain
Who Can Use It
- Data Scientists: For training predictive models for vehicle valuation and studying feature importance.
- Economists/Market Analysts: For identifying price elasticity, demand shifts, and trends in the German automotive sector.
- Students/Beginners: To practice fundamental data cleaning, exploratory data analysis, and statistical reporting.
- Automotive Industry Professionals: To benchmark used car prices and inventory characteristics.
Dataset Name Suggestions
- German Used Vehicle Listings 2016
- eBay Germany Auto Sales Data
- Used Car Price Prediction Dataset (Germany)
- 2016 German Auto Market Snapshot
Attributes
Original Data Source: eBay Germany Auto Sales Data
QUALITY