USED VECHICLE MARKET PRICE SEGMENT CLASSIFICATION AND OVERPRICING DETECTION USING VEHICLE SPECIFICATIONS

Abstract

The used vehicle market is highly dynamic, influenced by diverse factors such as vehicle
specifications, consumer demand, depreciation rates, and seller pricing strategies. Buyers often
face difficulty in determining whether a listed price is fair, while sellers struggle to align their
offerings with competitive market values. This research introduces a comprehensive framework
for market price segment classification and overpricing detection using vehicle specifications as
the primary input. Key attributes—including make, model, year of manufacture, mileage, fuel
type, transmission, and overall condition—are systematically analyzed to establish fair price
ranges.
The methodology integrates machine learning models for regression and classification to predict
baseline prices, while anomaly detection techniques are applied to identify listings that deviate
significantly from expected values. By segmenting vehicles into distinct price categories, the
system enables structured comparison across similar models and conditions. Experimental
evaluation demonstrates that the proposed approach enhances pricing transparency, reduces
buyer uncertainty, and provides sellers with actionable insights into competitive positioning.
The contribution of this work lies in bridging the gap between raw vehicle specifications and
intelligent pricing analytics, thereby fostering trust and efficiency in the used vehicle
marketplace. Beyond consumer applications, the framework can be extended to support
dealerships, online platforms, and financial institutions in valuation processes, ultimately
promoting a more balanced and data-driven ecosystem for vehicle transactions.. The used vehicle
market often suffers from inconsistent pricing and lack of transparency, making it difficult for
buyers to identify fair deals. This project proposes a machine learning-based system for price
segment classification and overpricing detection using vehicle specifications.