TY - JOUR
T1 - Customs classification for cross-border e-commerce based on text-image adaptive convolutional neural network
AU - Li, Guo
AU - Li, Na
N1 - Publisher Copyright:
© 2019, Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2019/12/1
Y1 - 2019/12/1
N2 - Customs classification is an essential international procedure to import cross-border goods traded by various companies and individuals. Proper classification of such goods with high efficiency in light of the rapidly increasing amount of international trade is still challenging. The current abundant e-commence data and advanced machine learning techniques provide an opportunity for cross-border e-commerce sellers to classify goods efficiently. Thus, in this paper, we propose a text-image adaptive convolutional neural network to effectively utilize website information and facilitate the customs classification process. The proposed model includes two independent submodels: one for text and the other for image. The submodels are fused by a novel method, which can adjust the value of parameters according to the model training result. Finally, we conduct a case study and comparison experiments based on a group of customs tariff codes and a data set from an e-commerce website. Experiment results indicate the effectiveness of text and image combination in performance improvement, the outperformance of the adaptive fusion method, as well as the potential of this approach when applied to customs classification.
AB - Customs classification is an essential international procedure to import cross-border goods traded by various companies and individuals. Proper classification of such goods with high efficiency in light of the rapidly increasing amount of international trade is still challenging. The current abundant e-commence data and advanced machine learning techniques provide an opportunity for cross-border e-commerce sellers to classify goods efficiently. Thus, in this paper, we propose a text-image adaptive convolutional neural network to effectively utilize website information and facilitate the customs classification process. The proposed model includes two independent submodels: one for text and the other for image. The submodels are fused by a novel method, which can adjust the value of parameters according to the model training result. Finally, we conduct a case study and comparison experiments based on a group of customs tariff codes and a data set from an e-commerce website. Experiment results indicate the effectiveness of text and image combination in performance improvement, the outperformance of the adaptive fusion method, as well as the potential of this approach when applied to customs classification.
KW - Convolutional neural network
KW - Cross-border e-commerce
KW - Customs classification
KW - Text and image classification
UR - http://www.scopus.com/inward/record.url?scp=85061276160&partnerID=8YFLogxK
U2 - 10.1007/s10660-019-09334-x
DO - 10.1007/s10660-019-09334-x
M3 - Article
AN - SCOPUS:85061276160
SN - 1389-5753
VL - 19
SP - 779
EP - 800
JO - Electronic Commerce Research
JF - Electronic Commerce Research
IS - 4
ER -