The Journal of Bigdata (한국빅데이터학회지)

Korea Bigdata Society (한국빅데이터학회)
권호 표지

A Study on Detection of Small Export Companies Utilizing Trade Exports Live Index

무역수출 라이브지수를 활용한 중소수출기업 발굴 연구

  • 김희천 (연세대학교 일반대학원 융합기술경영공학과) ;
  • 임춘성 (연세대학교 산업공학과) ;
  • 성주원 ((주)미소정보기술)
  • Received : 2019.11.29
  • Accepted : 2019.12.31
  • Published : 2019.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

There have been many discussions on export indices in trade exports, but there is no definite trade export index which can be explained by objective indicators. Korea International Trade Association (KITA), Korea Trade-Investment Promotion Agency (KOTRA), etc., but we are currently in the process of thinking about ways to express the capabilities of exporting companies. In this study, we constructed the AI data sets by setting the activity indicators such as the size of the company and the credit score, the number of transaction customers, the number of transactions, the number of items, the transaction volume, and the transaction period as features, Lightgbm. Using the Graph Neural Network as an industrial cluster classification model, the export live index which expresses the exportable capacity among companies, items, and business groups was calculated. This includes the past activity of the company from the current calculating index Objectivity.

무역수출 분야에서 수출 지수에 관한 논의는 수차례 있었으나 객관적 지표로 설명할 수 있는 명확한 무역수출 지수는 없다. 한국무역협회(KITA), 대한무역투자진흥공사(KOTRA) 등에서 지표를 만들고자 하는 시도를 하고 있으나 수출기업의 역량을 표현할 수 있는 방법에 대하여 현재 계속 고민 중이다. 이에 본 연구는 기업의 규모, 신용도와 같은 공시지표와 거래고객수, 거래횟수, 상품개수, 거래량, 거래기간 등의 활동지표를 feature로 설정하여 인공지능 학습 데이터 셋을 구축하고, 딥러닝 알고리즘에서 Lightgbm을 이용하여 수출 가능 기업에 대한 분류 모델을 제시한다. 또한 기업이 속한 산업 군집 분류 모델로 Graph Neural Network을 사용하여 기업간, 품목간, 사업군에서의 수출 가능 역량을 표현하는 수출 Live지수를 산출하였으며 이는 지수를 산출하는 현재로부터 기업의 과거 활동을 포함함으로써 객관성을 확보하였다.

Keywords

References

  1. Guolin Ke. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. 31st Conference on Neural Information Processing Systems, Long Beach, CA, USA. NIPS 2017.
  2. Lee, B. M. An Influence of the Fourth Industrial Revolution on International Trade and Countermeasure Strategies to Promote Export in Korea. Korea Trade Research Association. 2017.06. 1-24.
  3. Guolin Ke. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Data-science. 2018.06.
  4. Juanjuan Li. A hierarchical framework for ad inventory allocation in programmatic advertising markets. Electronic Commerce Research and Applications 31. 2018. 40-51. https://doi.org/10.1016/j.elerap.2018.09.001
  5. Yung-Chia Chang. Application of eXtreme gradient boosting trees in the construction of credit risk assessment models for financial institutions. Applied Soft Computing Journal 73. 2018. 914-920 https://doi.org/10.1016/j.asoc.2018.09.029
  6. Yung-Chia Chang. Combining Principal Component Analysis, Discrete Wavelet Transform and XGBoost to trade in the financial markets. Expert Systems With Applications 125. 2019. 181-194. https://doi.org/10.1016/j.eswa.2019.01.083
  7. Wen Zhang. DeRec: A data-driven approach to accurate recommendation with deep learning and weighted loss function. Electronic Commerce Research and Applications 31. 2018. 12-23. https://doi.org/10.1016/j.elerap.2018.08.001
  8. Yang Zhao. How knowledge contributor characteristics and reputation affect userpayment decision in paid Q&A? An empirical analysis from the perspectiveof trust theory. Electronic Commerce Research and Applications 31. 2018. 1-11. https://doi.org/10.1016/j.elerap.2018.07.001
  9. Cheng Chen. LightGBM-PPI: Predicting proteinprotein interactions through LightGBM with multi-information fusion. Chemometrics and Intelligent Laboratory Systems 191. 2019. 54-64. https://doi.org/10.1016/j.chemolab.2019.06.003
  10. Jianing Niu, Yongmei Sun. Noise-suppressing channel allocation indynamic DWDM-QKD networks using LightGBM. Optics Express Journal 27. 2019.10. 22-28
  11. Kim, B. H. (2011), The Impact of FinTech on Transactions in International Trade. Korea Trade Research Association. 2018.04. 126-157.
  12. Baoguang Tian. Predicting protein-protein interactions by fusing various Chou's pseudo components and using wavelet denoising approach. Journal of Theoretical Biology 462. 2019. 329-346. https://doi.org/10.1016/j.jtbi.2018.11.011
  13. Muhammad Tahir. Sequence based predictor for discrimination of enhancer and their types by applying general form of Chou's trinucleotide composition. Computer Methods and Programs in Biomedicine 146. 2017. 69-75. https://doi.org/10.1016/j.cmpb.2017.05.008
  14. Xiaojun Ma. Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGboost algorithms according to different high dimensional data cleaning. Electronic Commerce Research and Applications 31. 2018. 24-39. https://doi.org/10.1016/j.elerap.2018.08.002
  15. Wei Ou. Training attractive attribute classifiers based on opinion features extracted from review data. Electronic Commerce Research and Applications 32. 2018. 13-22. https://doi.org/10.1016/j.elerap.2018.10.003
  16. Xiaowen Cui. UbiSitePred: A novel method for improving the accuracy of ubiquitination sites prediction by using LASSO to select the optimal Chou's. pseudo components. Chemometrics and Intelligent Laboratory Systems 184. 2019. 28-43. https://doi.org/10.1016/j.chemolab.2018.11.012