Car Price Quotes Driven by Data-Comprehensive Predictions Grounded in Deep Learning Techniques

• Published in: Electronics (Basel) 2023-07, Vol.12 (14), p.3083
• Main Authors: Dutulescu, Andreea, Catruna, Andy, Ruseti, Stefan, Iorga, Denis, Ghita, Vladimir, Neagu, Laurentiu-Marian, Dascalu, Mihai
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Automobile industry; Automobiles; Computer architecture; Datasets; Decision making; Decision trees; Deep learning; Emerging markets; Energy consumption; Machine learning; Neural networks; Performance evaluation; Power; Prediction models; Prediction theory; Price quotations; Prices; Prices and rates; Regression analysis; Support vector machines; Training; Used automobiles; Used cars; Vehicles
• ISSN: 2079-9292; 2079-9292
• DOI: 10.3390/electronics12143083

The used car market has a high global economic importance, with more than 35 million cars sold yearly. Accurately predicting prices is a crucial task for both buyers and sellers to facilitate informed decisions in terms of opportunities or potential problems. Although various machine learning techniques have been applied to create robust prediction models, a comprehensive approach has yet to be studied. This research introduced two datasets from different markets, one with over 300,000 entries from Germany to serve as a training basis for deep prediction models and a second dataset from Romania containing more than 15,000 car quotes used mainly to observe local traits. As such, we included extensive cross-market analyses by comparing the emerging Romanian market versus one of the world’s largest and most developed car markets, Germany. Our study used several neural network architectures that captured complex relationships between car model features, individual add-ons, and visual features to predict used car prices accurately. Our models achieved a high R2 score exceeding 0.95 on both datasets, indicating their effectiveness in estimating used car prices. Moreover, we experimented with advanced convolutional architectures to predict car prices based solely on visual features extracted from car images. This approach exhibited transfer-learning capabilities, leading to improved prediction accuracy, especially since the Romanian training dataset was limited. Our experiments highlighted the most important factors influencing the price, while our findings have practical implications for buyers and sellers in assessing the value of vehicles. At the same time, the insights gained from this study enable informed decision making and provide valuable guidance in the used car market.