[논문]분리학습 모델을 이용한 수출액 예측 및 수출 유망국가 추천

장영진; 원종관; 이채록

doi:10.13088/jiis.2022.28.1.069

분리학습 모델을 이용한 수출액 예측 및 수출 유망국가 추천
Export Prediction Using Separated Learning Method and Recommendation of Potential Export Countries 원문보기

지능정보연구 = Journal of intelligence and information systems, v.28 no.1, 2022년, pp.69 - 88

장영진 (연세대학교 경영학과) , 원종관 (부산대학교 경영학과) , 이채록 (부산대학교 경영학과)

초록
AI-Helper

최근 코로나19 팬데믹으로 인해 전 세계 경제와 외교 상황에 급격한 변화가 일어나고 있으며, 수출 의존도가 높은 한국은 이러한 변화에 큰 영향을 받고 있다. 본 연구에서는 기업의 수출전략 수립 및 의사결정 지원을 위해 차년도 수출액 예측 모델을 구축하고, 모델의 예측 결과를 바탕으로 수출 유망국가 추천 방식을 제안한다. 본 연구에서는 모델이 다양한 정보를 학습할 수 있도록 국가별, 품목별, 거시경제 변수 등 선행 연구에서 중요하게 사용된 변수를 다방면으로 수집하였다. 수집한 데이터를 분석한 결과, 국가와 품목에 따라서 수출액의 분포가 매우 비대칭적인 것을 확인할 수 있었다. 따라서, 모델의 예측 성능을 향상시키고 설명력을 확보하기 위해서 분리학습 방식을 사용하였다. 분리학습은 전체 데이터를 동질적인 하위 그룹으로 분리하고 개별 모델을 구축하는 방식으로, 본 연구에서는 수출액을 기준으로 5개 구간으로 데이터를 분리하였다. 모델 학습 과정에서 구간별 특성을 반영하여 구간1부터 구간4까지는 LightGBM을 사용하고, 구간5는 지수이동평균을 사용하였으며 이를 통해 모델의 예측 성능을 향상시킬 수 있었다. 모델의 설명력 확보를 위해서 추가로 구간별 모델의 SHAP-value를 계산하고 중요도가 높은 변수를 제시했다. 또한, 본 연구에서는 예측 모델을 기반으로 2단계 수출 유망국가 추천 방식을 제안했다. 효율적인 수출 전략 수립을 위해서 BCG 매트릭스와 국가별 점수 산출 방식을 사용하였고, 품목별 유망 국가 순위와 수출 관련 주요 정보들을 제공하였다. 본 연구는 다양한 정보를 학습한 머신러닝 모델로 여러 국가와 품목에 대한 예측을 실시하고, 이 과정에서 분리학습 방식으로 예측 성능을 향상시켰다는 점에서 의의가 있다. 또한, 현재 무역 관련 서비스들이 과거 데이터에 기반한 정보를 제공하고 있음을 고려할 때, 본 연구에서 제안한 예측 모델과 유망국가 추천 방식은 기업들의 미래 수출 전략 수립 및 동향 파악에 유용하게 사용될 수 있을 것으로 기대된다.

Abstract ▼ AI-Helper

One of the characteristics of South Korea's economic structure is that it is highly dependent on exports. Thus, many businesses are closely related to the global economy and diplomatic situation. In addition, small and medium-sized enterprises(SMEs) specialized in exporting are struggling due to the spread of COVID-19. Therefore, this study aimed to develop a model to forecast exports for next year to support SMEs' export strategy and decision making. Also, this study proposed a strategy to recommend promising export countries of each item based on the forecasting model. We analyzed important variables used in previous studies such as country-specific, item-specific, and macro-economic variables and collected those variables to train our prediction model. Next, through the exploratory data analysis(EDA) it was found that exports, which is a target variable, have a highly skewed distribution. To deal with this issue and improve predictive performance, we suggest a separated learning method. In a separated learning method, the whole dataset is divided into homogeneous subgroups and a prediction algorithm is applied to each group. Thus, characteristics of each group can be more precisely trained using different input variables and algorithms. In this study, we divided the dataset into five subgroups based on the exports to decrease skewness of the target variable. After the separation, we found that each group has different characteristics in countries and goods. For example, In Group 1, most of the exporting countries are developing countries and the majority of exporting goods are low value products such as glass and prints. On the other hand, major exporting countries of South Korea such as China, USA, and Vietnam are included in Group 4 and Group 5 and most exporting goods in these groups are high value products. Then we used LightGBM(LGBM) and Exponential Moving Average(EMA) for prediction. Considering the characteristics of each group, models were built using LGBM for Group 1 to 4 and EMA for Group 5. To evaluate the performance of the model, we compare different model structures and algorithms. As a result, it was found that the separated learning model had best performance compared to other models. After the model was built, we also provided variable importance of each group using SHAP-value to add explainability of our model. Based on the prediction model, we proposed a second-stage recommendation strategy for potential export countries. In the first phase, BCG matrix was used to find Star and Question Mark markets that are expected to grow rapidly. In the second phase, we calculated scores for each country and recommendations were made according to ranking. Using this recommendation framework, potential export countries were selected and information about those countries for each item was presented. There are several implications of this study. First of all, most of the preceding studies have conducted research on the specific situation or country. However, this study use various variables and develops a machine learning model for a wide range of countries and items. Second, as to our knowledge, it is the first attempt to adopt a separated learning method for exports prediction. By separating the dataset into 5 homogeneous subgroups, we could enhance the predictive performance of the model. Also, more detailed explanation of models by group is provided using SHAP values. Lastly, this study has several practical implications. There are some platforms which serve trade information including KOTRA, but most of them are based on past data. Therefore, it is not easy for companies to predict future trends. By utilizing the model and recommendation strategy in this research, trade related services in each platform can be improved so that companies including SMEs can fully utilize the service when making strategies and decisions for exports.

주제어

표/그림 (20)

표 Literature Reviews on Trade Exports Prediction
그림 Distribution of Exports
표 Literature Reviews on Separate Learning
그림 Distribution of Exports by Group
표 Criteria of Separating Datasets (USD)
표 Descriptive Statistics by Group(USD)
그림 Research Framework
표 External Variable List
표 Derived Variable List
표 Model Description
표 Prediction Accuracy by Model Structure (USD)
표 Prediction Accuracy by Algorithm (USD)
그림 Group 1 - SHAP Value
그림 Group 2 - SHAP Value
그림 Group 3 - SHAP Value
그림 Group 4 - SHAP Value
그림 Recommendation Process
표 Scoring Items and Weights
그림 Example of Recommendation Results by Item
그림 Example of Recommendation Results by Country

참고문헌 (23)

Bae, S. W. and J. S. Yoo, "Predicting the Real Estate Price Index Using Machine Learning Methods and Time Series Analysis Model," Housing Studies Review, 26.1 (2018), 107-133.

상세보기
Cho, B. G., G. B. Park and S. H. Ha," Comparative Analysis for Real-Estate Price Index Prediction Models using Machine Learning Algorithms: LIME's Interpretability Evaluation," The Journal of Information Systems, 29.3 (2020), 119-144
Hong, S. W., et al., "A study on the export forecast model through the analysis of export determinants by country and economic region," Korea Institute for Industrial Economics & Trade, (2017), 1-142.
Hong, T. H. and E. M. Kim, "Predicting the Response of Segmented Customers for the Promotion Using Data Mining," Information Systems Review, 12(2), (2010), 75-88.
Jeon, H. J. and Y. M. Kim, "The Impacts of Logistics Performance on National Competitiveness," KOREA INTERNATIONAL COMMERCIAL REVIEW, 34 (2019), 99-116.
Joo, T. W. and S. B. Kim, "Time series forecasting based on wavelet filtering," Expert Systems with Applications, 42.8 (2015), 3868-3874.

상세보기
Ke, Guolin, et al., "Lightgbm: A highly efficient gradient boosting decision tree," Advances in neural information processing systems, 30 (2017), 3146-3154.
Kim, J. R., "Korea's Export Competitiveness to EU through RCA-CAC Analysis," Journal of European Union Studies, 50 (2018), 73-105.
Kim, S. R., et al., "A Study on the Selection of the Export Promising Commodities and the Development of Supporting Policy in the area of Health Industry," Korea Health Industry Development Institute, (2005).
Kim, T. I., et al., "A Comparative Analysis on the Export Competitiveness between Korea and China: Focusing on RCA and TSI," Asia-Pacific Journal of Business, 8 (2017), 57-73.
Lee, J. W., "Development of Export Leading Index and Analysis of Fitness," KEXIM OVERSEAS ECONOMIC REVIEW, (2006), 4-17.
Lee, M. S., S. B. Park and Y. S. Kwon, "A study on impacts of SMEs' recognition of the importance of cooperation and trust toward large customer companies upon enhanced inter-organization cooperations and the new," Journal of the Korean Entrepreneurship Socieity, 10 (2015), 71-94.
Lu Ning, et al., "A customer churn prediction model in telecom industry using boosting," IEEE Transactions on Industrial Informatics, 10.2 (2012), 1659-1665.
Lundberg, Scott M., and S. I. Lee, "A unified approach to interpreting model predictions," Proceedings of the 31st international conference on neural information processing systems. (2017), 4768-4777
Ma, H. S. and S. T. Kim, "A Study on the Changes in the Trade Environment of Korea and the Prospect of Trade between Korea and China after COVID-19," The e-Business Studies, 22.2 (2021), 89-103.
Ma, Xiaojun, et al., "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.

상세보기
Mo, S. W. and G. B. Kim, "Volatility of Export Volume and Export Value of Gwangyang Port Abstract," Journal of Korea Port Economic Association, 31.1 (2015), 1-14.
Morgan, T., Anokhin, S., Ofstein, L., and Friske, W., "SME response to major exogenous shocks: The bright and dark sides of business model pivoting," International Small Business Journal, 38(5) (2020), 369-379.

상세보기
Oh, D. Y., "An Analysis of the Determinants of Korean SMEsnm,' Exports," Journal of International Trade and Industry Studies, 17.2 (2012), 135-159.
Son, K. W., H. S. Jo, and H. C. Moon, "The Determinants of Korea's Export Using Global Logistics Performance Index (LPI)," Ocean Policy Research, 35.2 (2020), 103-132.
Yoe, T. D. and S. D. Ki, "An Analysis of the Trade Relations between Korea and the Baltic Nations," International Commerce and Information Review, 20.4 (2018), 79-105.
Yoo, J. S. and E. H. Jang, "A Study on the Trade Items and Scale of Domestic Import and Export Companies on the Amount of Customs Refund," THE INTERNATIONAL COMMERCE & LAW REVIEW, 84 (2019), 189-207.
Yun, S. H., "COVID-19 Pandemic and Democracy, Economic Growth," KIRI, 517, (2021), 8-14.

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증