Korea Trade Review (무역학회지)

Korea Trade Research Association (한국무역학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison of long-term forecasting performance of export growth rate using time series analysis models and machine learning analysis

시계열 분석 모형 및 머신 러닝 분석을 이용한 수출 증가율 장기예측 성능 비교

  • Seong-Hwi Nam (Department of Economics, Pukyung National University)
  • Received : 2021.12.10
  • Accepted : 2021.12.29
  • Published : 2021.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, various time series analysis models and machine learning models are presented for long-term prediction of export growth rate, and the prediction performance is compared and reviewed by RMSE and MAE. Export growth rate is one of the major economic indicators to evaluate the economic status. And It is also used to predict economic forecast. The export growth rate may have a negative (-) value as well as a positive (+) value. Therefore, Instead of using the ReLU function, which is often used for time series prediction of deep learning models, the PReLU function, which can have a negative (-) value as an output value, was used as the activation function of deep learning models. The time series prediction performance of each model for three types of data was compared and reviewed. The forecast data of long-term prediction of export growth rate was deduced by three forecast methods such as a fixed forecast method, a recursive forecast method and a rolling forecast method. As a result of the forecast, the traditional time series analysis model, ARDL, showed excellent performance, but as the time period of learning data increases, the performance of machine learning models including LSTM was relatively improved.

Keywords

References

  1. Basurko, Agirre E., Ibarra G. Berastegi and Madariaga I.(2006), "Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area", Environmental Modelling & Software, 21, 430-446. https://doi.org/10.1016/j.envsoft.2004.07.008
  2. Bae, Seong-Wan and Yu, Jung-Suk(2018), "Predicting the Real Estate Price Index Using Machine Learning Methods and Time Series Analysis Model", Housing Studies Review, 26(1), 107-133.
  3. Cai, Jiaying and Kim, Hag-Min(2020), "Analysis of South Korea's Export to China in Cross-Border Electronic Commerce Using VAR Model", International Commerce and Information Review, 22(4), 3-20.
  4. Cho, Jung-hyeong (2014), "A Study on Demand Forecasting of Export Goods Based on Vector Autoregressive Model : Subject to Each Small Passenger Vehicles Quarterly Exported to USA", International Commerce and Information Review, 16(3), 73-96. https://doi.org/10.15798/kaici.16.3.201406.73
  5. Cho, Young-Hee and Lee, Gye-Sung(2010), "A Study on Improving Prediction Accuracy by Modeling Multiple Similar Time Series", The Institute of Internet, Broadcasting and Communication (IIBC), 10(6), 137-143.
  6. Choe, Jong-Il and Park, Soon-Chan(2016), "A Study on the ICT Industry Export Forecast Using Bayesian VAR Model", Journal of International Trade & Commerce, 12(2), 515-527.
  7. Hong, Seong-Wook, Shin, Hyun-Soo, Park, Seong-Geun and Kim, Jeong-Hyeon(2017), "A study on the establishment of an export forecast model through the analysis of export determinants by country and economic region, Korea Institute for Industrial Economics and Trade, Report No. 2017-837, 1-143.
  8. Huang, Di, Zhang, Chenyu, Li, Qiang, Han, Huachun, Huang, Dawen, Li, Taotao and Wang, Chen(2020), "Prediction of Solar Photovoltaic Power Generation Based on MLP and LSTM neural networks", Preprints of the 4th IEEE Conference on Energy Internet and Energy System Integration, 2744-2748.
  9. Joo, Il-Taek and Choi, Seung-Ho(2018), "Stock Prediction Model based on Bidirectional LSTM Recurrent Neural Network", Korea Information Electron Communication Technology, 11(2), 204-208.
  10. Kang, Han-Gyoun and Kim, Sung-Kwon(2006), "A Comparative Analysis of the Effects of Korean Manufacturing FDI in China and the U.S.A. on the Part Exports in Korea Using VAR", Korean Jouranl of Business Administration, 19(5), 1645-1662.
  11. Karlik, Bekir and Vehbi A Olgac(2011), "Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks", International Journal of Artificial Intelligence And Expert Systems(IJAE), 1(4), 111-122.
  12. Kim, Jun-Bong, Oh, Seung-Chul and Seo, Ki-Sung(2016), "Comparison of MLR and SVR Based Linear and Nonlinear Regressions Compensation for Wind Speed Prediction", The Transactions of The Korean Institute of Electrical Engineers, 65(5), 851-856. https://doi.org/10.5370/KIEE.2016.65.5.851
  13. Kim, Dan-Woo(2021), "Design and Evaluation of Exchange Rate Prediction Model Based on Artificial Intelligence Neural Network and Machine Learning Algorithms", Doctorate Thesis, Gachon University.
  14. Kim, Ahn-Ho(2001), "A Consistent Estimation of Export and Import in Korea", Journal of Industrial Economics and Business, 14(5), 117-130.
  15. Lee, Eun-Kyung(2016), "Analysis on the Relationship between Higher Education and Economic Growth: Focused on Korea and Japan", The Journal of Economics and Finance of Education, 25(2),129-150.
  16. Lee, Sung-Yhun and Ahn, Ki-Myung(2020), "Study on the Forecasting and Relationship of Busan Cargo by ARIMA and VAR.VEC", Korean Institute of Navigation and Port Research, 44(1), 44-52.
  17. Lee, Sang-Ho(1998), "A Consistent Estimation of Korea's Export Function", Journal of International Trade and Industry Studies, 3(2), 3-15.
  18. Martinez, Francisco, Maria P. Frias, Francisco Charte and Antonio J. Rivera(2019), "Time Series Forecasting with KNN in R: the tsfknn Package", The R Journal, 11(2), 229-242. https://doi.org/10.32614/RJ-2019-004
  19. Nakkiran, Preetum, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak and Ilya Sutskever(2020), "Deep Double Descent: Where Bigger Models and More Data Hurt", ICLR 2020 Conference Paper, 1-24.
  20. ulke, Volkan, Afsin Sahin and Abdulhamit Subasi(2018), "A comparison of time series and machine learning models for inflation forecasting: empirical evidence from the USA", Neural Comput & Applic, 30, 1519-1527. https://doi.org/10.1007/s00521-016-2766-x
  21. Xu, Zhikun, Gao, Yabin and Jin, Ying-Ying(2014), "Application of an Optimized SVR Model of Machine Learning", International Journal of Multimedia and Ubiquitous Engineering, 9(6), 67-80.
  22. Yi, Chae-Deug(2021), "Investment, Export, and Exchange Rate on Prediction of Employment with Decision Tree, Random Forest, and Gradient Boosting Machine Learning Models", Korea Trade Review, 46(2), 281-299. https://doi.org/10.22659/KTRA.2021.46.2.281
  23. Zhu, Shiyou, Lee, Min-Hwan, and Hwang, Kyu-Sun(2010), "The Exchange Rate Pass-through Effects on Korean Import and Consumer Prices Using a Structural VAR Model", The Korean Economic and Business Association, 28(2), 85-108.