跳到主要內容

臺灣博碩士論文加值系統

(34.204.198.73) 您好!臺灣時間:2024/07/19 14:28
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:彭品蓉
研究生(外文):PENG, PIN-JUNG
論文名稱:臺灣進出口值之預測─傳統方法與深度學習法之比較
論文名稱(外文):Forecasting Import and Export of Taiwan - Comparison of Traditional Methods and Deep Learning Methods
指導教授:李政峯李政峯引用關係
指導教授(外文):LEE, CHENG-FENG
口試委員:欉清全蔡麗茹李政峯
口試委員(外文):TSONG,CHING-CHUANTSAI,LI-JULEE, CHENG-FENG
口試日期:2023-06-02
學位類別:碩士
校院名稱:國立高雄科技大學
系所名稱:企業管理系
學門:商業及管理學門
學類:企業管理學類
論文種類:學術論文
論文出版年:2023
畢業學年度:111
語文別:中文
論文頁數:68
中文關鍵詞:深度學習進出口值預測景氣循環
外文關鍵詞:Deep LearningForecastLSTMCNN
相關次數:
  • 被引用被引用:0
  • 點閱點閱:60
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
鑒於台灣高度依賴進出口貿易的情境,準確預測進出口值對於政府政策和企業決策制定具有重要意義。然而,由於進出口貿易值與景氣循環變數之間存在著複雜的非線性關係,進出口值的預測變得困難。因此,本研究旨在利用經濟結構模型、時間序列模型、長短期記憶神經網絡(LSTM)模型以及卷積神經網絡(CNN)+ LSTM 模型,尋找最精確的預測模型。

實證結果顯示,相較於其他模型,CNN+LSTM 模型在預測進出口值方面表現最佳。該模型相對於經濟結構模型可降低 38%至 70%的平均絕對百分比誤差(MAPE),相對於時間序列模型可降低 22%至 27%的 MAPE,以及相對於LSTM 模型可降低 35%至 49%的 MAPE。這一結果證實了在處理大量變數時,將 CNN 的圖像辨識能力應用於經濟解釋是可行的。通過將 CNN 用於降維處理並將其輸入LSTM 模型,我們能夠獲得最佳的預測結果。

Accurately predicting import and export values is significant for government policies and business decision-making in the context of Taiwan's high dependence on international trade. However, due to the complex non-linear relationship between trade values and business cycle variables, predicting import and export values becomes challenging. Therefore, this study aims to identify the most accurate prediction model by utilizing economic structure models, time series models, Long Short-Term Memory (LSTM) models, and Convolutional Neural Network (CNN) + LSTM models.

The empirical results demonstrate that the CNN+LSTM model outperforms other models in predicting import and export values. Compared to the economic structure model, the CNN+LSTM model reduces the Mean Absolute Percentage Error (MAPE) by 38% to 70%. Moreover, it reduces the MAPE by 22% to 27% compared to the time series model and by 35% to 49% compared to the LSTM model. These findings confirm the feasibility of incorporating CNN's image recognition capabilities into economic interpretation when dealing with numerous variables. By utilizing CNN for dimensionality reduction and feeding the results into the LSTM model, we achieve optimal prediction outcomes.
中文摘要 i
英文摘要 ii
致謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
第一節 研究背景 1
第二節 研究動機 2
第三節 研究目的 5
第二章 文獻探討 6
第一節 國際貿易 6
壹 、貿易 6
貳 、出口 7
參 、進口 9
第二節 傳統貿易預測 11
壹 、經濟結構模型─出口需求函數 11
貳 、經濟結構模型─進口需求函數 12
參、時間數列方法 13
第三節 景氣循環 16
壹、景氣循環與貿易 16
貳、景氣循環同步現象 16
第四節 人工智慧(Artificial Intelligence, AI) 18
壹、卷積神經網路(Convolutional Neural Network, CNN) 18
貳、長短期記憶神經網路( Long Short-Term Memory, LSTM) 18
參、應用─財務金融領域 19
肆、應用─貿易領域 20
第三章 研究方法 22
第一節 研究變數 22
第二節 傳統預測方法 23
壹 、經濟結構模型 23
貳 、時間數列模型 24
第三節 深度學習法 26
壹 、卷積神經網路(Convolutional Neural Network, CNN) 26
貳 、長短期記憶模型(Long Short‐Term Memory,LSTM) 27
第四節 預測績效評估 30
第四章 研究結果 31
第一節 研究資料 31
壹 、資料來源 31
貳、資料預處理 34
第二節 傳統預測方法 35
壹 、經濟結構模型 35
貳 、時間序列模型 36
第三節 深度學習法 38
壹 、長短期記憶模型(LSTM) 38
貳 、卷積神經網路(CNN)+長短期記憶模型(LSTM) 45
第四節 傳統預測方法與深度學習法之比較 47
第五章 結論與建議 48
第一節 研究結論 48
第二節 研究貢獻 49
第三節 研究限制及未來建議 50
參考文獻 51
中文參考文獻 51
英文參考文獻 52
中文參考文獻
李政峯(2021)。後疫情時代全球貿易趨勢之預測:深度學習之應用。科技部110年度專題研究計畫。 蕭宇翔、林依伶(2020)。臺灣景氣狀態之預測。臺灣經濟預測與政策,51:1,1-56。
黃裕烈、徐之強、張瑞雲(2019)。景氣監測預警系統之研究。國家發展委員會研究報告(報告編號:(108)015.0205),未出版。
周大森(2019)。運用大量數據認定景氣轉折點。國家發展委員會研究報告(報告編號:(108)020.0209),未出版。
何宗武、葉國俊、張淑華、林雅淇(2020)。運用人工智慧掌握景氣動態。國家發展委員會研究報告(報告編號:(109)025.0205),未出版。

英文參考文獻
A. Giles, J., & Williams, C. L. (2000). Export-led growth: a survey of the empirical literature and some non-causality results. Part 1. The Journal of International Trade & Economic Development, 9(3), 261-337.
Abdel-Hamid, O., Mohamed, A.-r., Jiang, H., Deng, L., Penn, G., & Yu, D. (2014). Convolutional neural networks for speech recognition. IEEE/ACM Transactions on audio, speech, and language processing, 22(10), 1533-1545.
Aditya, A., & Acharyya, R. (2013). Export diversification, composition, and economic growth: Evidence from cross-country analysis. The Journal of International Trade & Economic Development, 22(7), 959-992.
Ali, G., & Li, Z. (2018). Exports-led growth or growth-led exports in the case of China and Pakistan: An empirical investigation from the ARDL and Granger causality approach. The International Trade Journal, 32(3), 293-314.
Alimi, S. R., & Muse, B. O. (2012). Export-led growth or growth–driven exports? Evidence from Nigeria.
Allegret, J.-P., & Essaadi, E. (2011). Business cycles synchronization in East Asian economy: Evidences from time-varying coherence study. Economic Modelling, 28(1-2), 351-365.
Amat, C., Michalski, T., & Stoltz, G. (2018). Fundamentals and exchange rate forecastability with simple machine learning methods. Journal of International Money and Finance, 88, 1-24.
Araujo, R. A., Teixeira, J. R., & Soares, C. (2015). Export-led growth vs growth-led exports: what matters for the Brazilian growth experience after trade liberalization? Review of Keynesian Economics, 3(1), 108-128.
Arize, A. C. (2001). Traditional export demand relation and parameter instability: An empirical investigation. Journal of Economic Studies.
Arize, A. C., Osang, T., & Slottje, D. J. (2000). Exchange-rate volatility and foreign trade: evidence from thirteen LDC's. Journal of Business & Economic Statistics, 18(1), 10-17.
Arumugam, P., & Anithakumari, V. (2013). Fuzzy time series method for forecasting Taiwan export data. International Journal of Engineering Trends and Technology (IJETT)-Volume4 Issue8-August.
Awokuse, T. O. (2006). Export-led growth and the Japanese economy: evidence from VAR and directed acyclic graphs. Applied Economics, 38(5), 593-602.
Awokuse, T. O. (2007). Causality between exports, imports, and economic growth: Evidence from transition economies. Economics letters, 94(3), 389-395.
Awokuse, T. O. (2008). Trade openness and economic growth: is growth export-led or import-led? Applied Economics, 40(2), 161-173.
Bahmani-Oskooee, M., & Economidou, C. (2009). Export led growth vs. growth led exports: LDCs experience. The Journal of Developing Areas, 42(2), 179-209.
Bahmani-Oskooee, M., & Niroomand, F. (1999). Openness and economic growth: an empirical investigation. Applied Economics Letters, 6(9), 557-561.
Balassa, B. (1978). Exports and economic growth: further evidence. Journal of development Economics, 5(2), 181-189.
Berdiev, A. N., & Chang, C.-P. (2015). Business cycle synchronization in Asia-Pacific: New evidence from wavelet analysis. Journal of Asian Economics, 37, 20-33.
Bhagwati, J. N. (1988). Export-promoting trade strategy: issues and evidence. The World Bank Research Observer, 27-57.
Biswal, B., & Dhawan, U. (1998). Export-led growth hypothesis: cointegration and causality analysis for Taiwan. Applied Economics Letters, 5(11), 699-701.
Bucci, A. (2020). Cholesky–ANN models for predicting multivariate realized volatility. Journal of Forecasting, 39(6), 865-876.
Calderon, C., Chong, A., & Stein, E. (2007). Trade intensity and business cycle synchronization: Are developing countries any different? Journal of international Economics, 71(1), 2-21.
Çetintaş, H., & Barişik, S. (2009). Export, import and economic growth: The case of transition economies. Transition Studies Review, 15(4), 636-649.
Chawla, D., & Behl, R. (2002). Forecast of Indian Readymade Garments Exports Using the ARIMA Model. Global Business Review, 3(1), 63-76.
Chen, S., Song, Y., Ding, Y., Zhang, M., & Nie, R. (2021). Using long short-term memory model to study risk assessment and prediction of China’s oil import from the perspective of resilience theory. Energy, 215, 119152.
Chen, S.-W. (2008). Long-run aggregate import demand function in Taiwan: an ARDL bounds testing approach. Applied Economics Letters, 15(9), 731-735.
Chen, Y., He, K., & Tso, G. K. (2017). Forecasting crude oil prices: a deep learning based model. Procedia Computer Science, 122, 300-307.
Chou, W. L. (2000). Exchange rate variability and China's exports. Journal of Comparative Economics, 28(1), 61-79.
Coe, D. T., & Helpman, E. (1995). International r&d spillovers. European economic review, 39(5), 859-887.
Culkin, R., & Das, S. R. (2017). Machine learning in finance: the case of deep learning for option pricing. Journal of Investment Management, 15(4), 92-100.
Dash, A. K., Dutta, S., & Paital, R. R. (2018). Bilateral export demand function of India: An empirical analysis. Theoretical Economics Letters, 8(11), 2330-2344.
Dave, E., Leonardo, A., Jeanice, M., & Hanafiah, N. (2021). Forecasting Indonesia exports using a hybrid model ARIMA-LSTM. Procedia Computer Science, 179, 480-487.
Duan, Y., Yisheng, L., & Wang, F.-Y. (2016). Travel time prediction with LSTM neural network. 2016 IEEE 19th international conference on intelligent transportation systems (ITSC),
Dutta, D., & Ahmed, N. (1999). An aggregate import demand function for Bangladesh: a cointegration approach. Applied Economics, 31(4), 465-472.
Dutta*, D., & Ahmed, N. (2004). An aggregate import demand function for India: a cointegration analysis. Applied Economics Letters, 11(10), 607-613.
Edwards, S. (1998). Openness, productivity and growth: what do we really know? The Economic Journal, 108(447), 383-398.
Emery, R. F. (1967). The relation of exports and economic growth. Kyklos, 20(4), 470-486.
Farooqi, A. (2014). ARIMA model building and forecasting on imports and exports of Pakistan. Pakistan Journal of Statistics and Operation Research, 157-168.
Fukushima, K., & Miyake, S. (1982). Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition. In Competition and cooperation in neural nets (pp. 267-285). Springer.
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to forget: Continual prediction with LSTM. Neural computation, 12(10), 2451-2471.
Ghosh, S. (2017). Forecasting Cotton Exports in India using the ARIMA model. Amity Journal of Economics, 2(2), 36-52.
Hausmann, R., Hwang, J., & Rodrik, D. (2007). What you export matters. Journal of economic growth, 12(1), 1-25.
Heaton, J. B., Polson, N. G., & Witte, J. H. (2017). Deep learning for finance: deep portfolios. Applied Stochastic Models in Business and Industry, 33(1), 3-12.
Hopp, D. (2022). Benchmarking Econometric and Machine Learning Methodologies in Nowcasting. arXiv preprint arXiv:2205.03318.
Hossain, A. A. (2009). Structural change in the export demand function for Indonesia: Estimation, analysis and policy implications. Journal of Policy Modeling, 31(2), 260-271.
Iyidoğan, P. V., Dalgiç, B., & Akbulut, H. (2017). Is there a non-linear relationship between trade and growth? A panel threshold analysis for Central and Eastern European countries. Acta Oeconomica, 67(1), 117-136.
Kabir, R. (1988). Estimating import and export demand function: The case of Bangladesh. The Bangladesh Development Studies, 16(4), 115-127.
Keck, A., Raubold, A., & Truppia, A. (2010). Forecasting international trade: A time series approach. OECD Journal: Journal of Business Cycle Measurement and Analysis, 2009(2), 157-176.
Khan, T. (2011). Identifying an appropriate forecasting model for forecasting total import of Bangladesh. Statistics in Transition new series, 12(1), 179-192.
Kongcharoen, C., & Kruangpradit, T. (2013). Autoregressive integrated moving average with explanatory variable (ARIMAX) model for Thailand export. 33rd International Symposium on Forecasting, South Korea,
Kose, M. A., & Yi, K.-M. (2006). Can the standard international business cycle model explain the relation between trade and comovement? Journal of international Economics, 68(2), 267-295.
Kumar, G., & Gupta, S. (2010). Forecasting Exports of Industrial Goods from Punjab-An Application of Univariate ARIMA Model. Annals of the University of Petrosani, Economics, 10(4), 169-180.
Kumar, S. (2011). Estimating export demand equations in selected Asian countries. Journal of Chinese Economic and Foreign Trade Studies.
Lawrence, R. Z., & Weinstein, D. (1999). Trade and growth: import-led or export-led? Evidence from Japan and Korea. In: National bureau of economic research Cambridge, Mass., USA.
Lee, S. I., & Yoo, S. J. (2020). Multimodal deep learning for finance: integrating and forecasting international stock markets. The Journal of Supercomputing, 76(10), 8294-8312.
Liu, Y. (2021). Foreign Trade Export Forecast Based on Fuzzy Neural Network. Complexity, 2021.
Mahadevan, R., & Suardi, S. (2008). A dynamic analysis of the impact of uncertainty on import-and/or export-led growth: The experience of Japan and the Asian Tigers. Japan and the World Economy, 20(2), 155-174.
Maitra, B. (2020). Exploring import-led growth in India: Evidence from the post-reform period. South Asian Journal of Macroeconomics and Public Finance, 9(1), 87-113.
Mazumdar, J. (2001). Imported machinery and growth in LDCs. Journal of development Economics, 65(1), 209-224.
Moneta, F., & Rüffer, R. (2009). Business cycle synchronisation in East Asia. Journal of Asian Economics, 20(1), 1-12.
Mosikari, T. J., & Eita, J. H. (2020). Modelling asymmetric relationship between exports and growth in a developing economy: Evidence from Namibia. South African Journal of Economic and Management Sciences, 23(1), 1-10.
Mujahid, N., Begam, A., Shamshir, M., Zeb, A., & Phil, M. (2019). Import-led growth hypothesis: A case study of Pakistan. Journal of Economics and Sustainable Development, 10(8), 20-28.
Narayan, S., & Narayan, P. K. (2005). An empirical analysis of Fiji's import demand function. Journal of Economic Studies.
Narayan, S., & Narayan, P. K. (2010). Estimating import and export demand elasticities for Mauritius and South Africa. Australian economic papers, 49(3), 241-252.
O'Shea, K., & Nash, R. (2015). An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458.
Park, Y.-J. (2013). Regional business cycles in East Asia: synchronization and its determinants. Journal of East Asian Economic Integration, 17(2), 103-128.
Prasad, E. S. (1999). International trade and the business cycle. The Economic Journal, 109(458), 588-606.
Qu, Q., Li, Z., Tang, J., Wu, S., & Wang, R. (2019). A trend forecast of import and export trade total volume based on LSTM. IOP Conference Series: Materials Science and Engineering,
Raghutla, C., & Chittedi, K. R. (2020). Is there an export‐or import‐led growth in emerging countries? A case of BRICS countries. Journal of Public Affairs, 20(3), e2074.
Ram, R. (1985). Exports and economic growth: Some additional evidence. Economic Development and Cultural Change, 33(2), 415-425.
Rangasamy, L. (2009). Exports and economic growth: The case of South Africa. Journal of International Development: The Journal of the Development Studies Association, 21(5), 603-617.
Richards, D. G. (2001). Exports as a determinant of long-run growth in Paraguay, 1966-96. Journal of Development Studies, 38(1), 128-146.
SaangJoon, B. (2008). The bilateral real exchange rates and trade between China and the US. China Economic Review, 19(2), 117-127.
Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied soft computing, 90, 106181.
Shin, K., & Wang, Y. (2003). Trade integration and business cycle synchronization in East Asia. Asian Economic Papers, 2(3), 1-20.
Shen, M. L., Lee, C. F., Liu, H. H., Chang, P. Y., & Yang, C. H. (2021).Effective multinational trade forecasting using LSTM recurrent neural network. Expert Systems with Applications, 182, 115199.
Simard, P. Y., Steinkraus, D., & Platt, J. C. (2003). Best practices for convolutional neural networks applied to visual document analysis. Icdar,
Sirignano, J., & Cont, R. (2019). Universal features of price formation in financial markets: perspectives from deep learning. Quantitative Finance, 19(9), 1449-1459.
Staudemeyer, R. C., & Morris, E. R. (2019). Understanding LSTM--a tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586.
Stock, J. H., & Watson, M. W. (2002). Forecasting using principal components from a large number of predictors. Journal of the American statistical association, 97(460), 1167-1179.
Sultan, Z. A. (2014). Saudi’s export demand function: The ARDL approach. Journal of Economics and Sustainable Development, 5(3), 200-206.
Tang, T. C. (2003). An empirical analysis of China's aggregate import demand function. China Economic Review, 14(2), 142-163.
Tang, T. C. (2003). Japanese aggregate import demand function: reassessment from the ‘bounds’ testing approach. Japan and the World Economy, 15(4), 419-436.
Tang, T. C., & Nair, M. (2002). A cointegration analysis of Malaysian import demand function: reassessment from the bounds test. Applied Economics Letters, 9(5), 293-296.
Upadhyay, V. (2013). Modelling and forecasting export and import of Indian wood based panel using ARIMA models. Elixir International Journal, Statistics, 63, 18145-18148.
Wang, C.-C. (2011). A comparison study between fuzzy time series model and ARIMA model for forecasting Taiwan export. Expert Systems with Applications, 38(8), 9296-9304.
Wang, P. (2017). Time series analysis of China's service trade based on ARIMA model. 2017 International Conference on Economics, Finance and Statistics (ICEFS 2017),
Yamashita, R., Nishio, M., Do, R. K. G., & Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into imaging, 9(4), 611-629.
Yu, L., Wang, S., & Lai, K. K. (2007). A hybrid econometric-AI ensemble learning model for Chinese foreign trade prediction. International Conference on Computational Science,
Zhang, Y. (2019). Application of improved BP neural network based on e-commerce supply chain network data in the forecast of aquatic product export volume. Cognitive Systems Research, 57, 228-235.
Zhao, Z., Chen, W., Wu, X., Chen, P. C., & Liu, J. (2017). LSTM network: a deep learning approach for short‐term traffic forecast. IET Intelligent Transport Systems, 11(2), 68-75.
電子全文 電子全文(網際網路公開日期:20280723)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊