Predicting Auction Price of Vehicle License Plate with Deep Residual Learning
This addresses a high-stakes, domain-specific problem in auction pricing for license plates in China, but it is incremental as it applies existing deep learning methods to a new dataset.
The paper tackles the problem of predicting auction prices for Chinese license plates, which can reach millions, by developing an end-to-end neural network model that outperforms simpler machine learning methods, with convolutional networks showing better performance than recurrent networks.
Due to superstition, license plates with desirable combinations of characters are highly sought after in China, fetching prices that can reach into the millions in government-held auctions. Despite the high stakes involved, there has been essentially no attempt to provide price estimates for license plates. We present an end-to-end neural network model that simultaneously predict the auction price, gives the distribution of prices and produces latent feature vectors. While both types of neural network architectures we consider outperform simpler machine learning methods, convolutional networks outperform recurrent networks for comparable training time or model complexity. The resulting model powers our online price estimator and search engine.