British Pre-Owned Vehicle Ledger

Columns

• index: Unique identifier for the record.
• make: The manufacturer of the vehicle (e.g., Mercedes-Benz, BMW).
• model: The specific model of the vehicle (e.g., C Class, A Class).
• variant: The specific trim or version of the model (e.g., SE, TDI).
• car_price: The listed price of the vehicle in GBP.
• car_badges: Highlights or badges associated with the listing (e.g., 'Good price', 'Finance available').
• car_title: The main title of the advertisement.
• car_sub_title: Additional descriptive text for the advertisement.
• car_attention_grabber: Marketing text used to attract buyers (e.g., '2 years free servicing').
• car_specs: A string containing technical specifications (e.g., SUV, 1.5L, Manual, Petrol).
• car_seller: The type of seller (e.g., Private seller, Cazoo).
• car_seller_rating: The numerical rating of the seller (1-5 scale).
• car_seller_location: The geographic location of the seller (e.g., Peterborough, Birmingham).
• year: The vehicle's year of manufacture.
• reg: The registration plate series (e.g., 19 reg).
• body_type: The category of the vehicle body (e.g., SUV, hatchback).
• miles: The total mileage recorded on the vehicle.
• engine_vol: The volume of the engine.
• engine_size: The size of the engine.
• engine_size_unit: The unit of measurement for engine size (e.g., ps, bhp).
• transmission: The type of transmission (Manual vs Automatic).
• feul_type: The type of fuel required (e.g., Petrol, Diesel).
• num_owner: The number of previous owners.
• ulez: Indicator of whether the vehicle is ULEZ (Ultra Low Emission Zone) compliant.
• full_service: Indicator of a full service history.
• part_service: Indicator of a partial service history.
• part_warranty: Indicator of available part warranty.
• full_dealership: Indicator of full dealership history or status.
• first_year_road_tax: Indicator if the first year of road tax is included.
• brand_new: Indicator if the vehicle is brand new.
• finance_available: Indicator if finance options are available.
• discounted: Indicator if the vehicle price is discounted.

Distribution

• Format: Tabular data in CSV format (all_car_adverts.csv).
• Size: Approximately 279.27 MB.
• Structure: Contains over 1 million original rows, processed down to roughly 818,000 valid records after cleaning. The dataset features 32 columns per record.
• Sorting: Data is sorted alphabetically by make, model, and variant.

Usage

• Price Prediction Models: Training machine learning algorithms to estimate vehicle value based on mileage, age, and specifications.
• Market Trend Analysis: Evaluating the popularity of specific brands, fuel types (petrol vs diesel), and body types (SUV vs hatchback) in the UK market.
• Depreciation Studies: Analysing how vehicle value decreases over time and mileage for different manufacturers.
• Inventory Management: Assisting dealerships in understanding competitive pricing and stock levels in various locations.
• Exploratory Data Analysis (EDA): Visualising relationships between seller ratings, location, and pricing strategies.

Coverage

• Geographic Scope: United Kingdom (locations include Peterborough, Birmingham, and others).
• Time Range: October 2022.
• Demographic/Content Scope: Covers a wide range of vehicle types, predominantly SUVs (37%) and Hatchbacks (33%), with a mix of private and trade sellers. Includes petrol (51%) and diesel (40%) vehicles.

License

Who Can Use It

• Data Scientists & Analysts: For practicing data cleaning, visualisation, and regression modelling.
• Automotive Economists: For assessing the health and trends of the secondary car market.
• Car Dealerships: For competitive intelligence and pricing strategy formulation.
• Consumer Advocates: For analysing the prevalence of financing options and seller reliability.

Dataset Name Suggestions

• UK Used Car Market Listings (October 2022)
• British Pre-Owned Vehicle Ledger
• GB Automotive Pricing & Specifications Database
• United Kingdom Vehicle Sales Snapshot 2022

Attributes