近年來，隨著全球半導體產業的迅速發展，國際IC供應鏈中的不確定性和複雜性日益增加，高科技產業公司若想在全球市場中占有一席之地，就必須掌握未來全球需求的動向。眾多現有的半導體預測研究主要集中在訂單預測上，但由於數據集的限制和不公開性質，這類研究在實務驗證和實施時面臨著諸多挑戰，因此整體市場的預測研究變得尤為關鍵，這不僅有助於企業更好地應對市場變化，還能為其制定長期策略提供關鍵依據，從而提升其在全球市場中的競爭力。本研究旨在利用公開數據集識別影響全球半導體需求的關鍵因素，並以此制定以半導體產業領先指標為主的需求預測框架。
研究的初步階段將專注於建立半導體銷售與外部指標之間的關聯性，其中半導體銷售將參考世界半導體貿易統計協會(World Semiconductor Trade Statistics，WSTS) 統計之每月全球半導體營收數據，而外部指標則包含如美國工業生產指數、納斯達克指數、台灣半導體設備進口金額等 11 項公開指標資料，本研究擬通過因果分析方法，找出對半導體市場需求動態有顯著影響的領先指標。在初步確定這些領先指標的基礎上，本研究將開發以機器學習和深度學習為主的多變量預測模型，並針對不同的時間預測區間和訓練時間窗進行實驗設計。通過比較不同模型和條件下的領先指標與其他特徵篩選方法，驗證領先指標篩選結果在半導體市場需求預測中的效能，增強整體預測框架的穩健性和可靠性。

In recent years, the rapid development of the global semiconductor industry has increased uncertainty and complexity within the international IC supply chain. To remain competitive, high-tech companies must understand future trends. Many existing semiconductor forecasts focus on order predictions but face challenges due to data limitations and lack of transparency. Thus, comprehensive market forecasting is essential, providing insights for long-term strategy and enhancing global competitiveness. This study aims to identify key factors influencing global semiconductor demand using publicly available data and establishing a forecasting framework based on leading industry indicators.
Initially, the research will correlate semiconductor sales with external indicators, referencing data from the World Semiconductor Trade Statistics (WSTS) and including metrics like the US Industrial Production Index, NASDAQ Index, and Taiwan's semiconductor equipment import value. Through causal analysis, the study will identify significant leading indicators affecting market demand dynamics. Based on these indicators, the study will develop multivariate forecasting models using machine learning and deep learning. Experimental designs will cover various forecasting intervals and training windows. By comparing different models and feature selection methods, the study aims to validate the effectiveness of these leading indicators in predicting semiconductor market demand, thus enhancing the robustness and reliability of the forecasting framework.

Aubry, M., & Renou-Maissant, P. (2013). Investigating the semiconductor industry cycles. Applied Economics, 45(21), 3058-3067. https://doi.org/10.1080/00036846.2012.697123
Aubry, M., & Renou-Maissant, P. (2014). Semiconductor industry cycles: Explanatory factors and forecasting. Economic Modelling, 39, 221-231. https://doi.org/10.1016/j.econmod.2014.02.039
Berge, T. J. (2015). Predicting Recessions with Leading Indicators: Model Averaging and Selection over the Business Cycle. Journal of Forecasting, 34(6), 455-471. https://doi.org/10.1002/for.2345
Chien, C.-F., Lin, Y.-S., & Lin, S.-K. (2020). Deep reinforcement learning for selecting demand forecast models to empower Industry 3.5 and an empirical study for a semiconductor component distributor. International Journal of Production Research, 58(9), 2784-2804. https://doi.org/10.1080/00207543.2020.1733125
Chow, H. K., & Choy, K. M. (2006). Forecasting the global electronics cycle with leading indicators: A bayesian var approach. International Journal of Forecasting, 22(2), 301-315.
Comincioli, B. (1996). The stock market as a leading indicator: An application of granger causality. University avenue undergraduate journal of economics, 1(1), 1.
Croux, C., & Reusens, P. (2013). Do stock prices contain predictive power for the future economic activity? A Granger causality analysis in the frequency domain. Journal of Macroeconomics, 35, 93-103. https://doi.org/10.1016/j.jmacro.2012.10.001
Gao, X., Li, X., Zhao, B., Ji, W., Jing, X., & He, Y. (2019). Short-Term Electricity Load Forecasting Model Based on EMD-GRU with Feature Selection. Energies, 12(6). https://doi.org/10.3390/en12061140
Granger, C. W. (1969). Investigating causal relations by econometric models and cross-spectral methods. Econometrica: journal of the Econometric Society, 424-438.
Hamidi, O., Tapak, L., Abbasi, H., & Maryanaji, Z. (2017). Application of random forest time series, support vector regression and multivariate adaptive regression splines models in prediction of snowfall (a case study of Alvand in the middle Zagros, Iran). Theoretical and Applied Climatology, 134(3-4), 769-776. https://doi.org/10.1007/s00704-017-2300-9
Liu, C., Hu, Z., Li, Y., & Liu, S. (2017). Forecasting copper prices by decision tree learning. Resources Policy, 52, 427-434. https://doi.org/10.1016/j.resourpol.2017.05.007
Liu, W.-H. (2005). Determinants of the semiconductor industry cycles. Journal of Policy Modeling, 27(7), 853-866. https://doi.org/10.1016/j.jpolmod.2005.05.009
Liu, W.-H. (2007). Forecasting the semiconductor industry cycles by bootstrap prediction intervals. Applied Economics, 39(13), 1731-1742. https://doi.org/10.1080/00036840600706995
Liu, W.-H., & Chyi, Y.-L. (2006). A Markov regime-switching model for the semiconductor industry cycles. Economic Modelling, 23(4), 569-578. https://doi.org/10.1016/j.econmod.2006.02.007
Liu, W.-H., & Weng, S.-S. (2016). On predicting the semiconductor industry cycle: a Bayesian model averaging approach. Empirical Economics, 54(2), 673-703. https://doi.org/10.1007/s00181-016-1198-x
Mushtaq, R. (2011). Augmented dickey fuller test.
Sapankevych, N., & Sankar, R. (2009). Time Series Prediction Using Support Vector Machines: A Survey. IEEE Computational Intelligence Magazine, 4(2), 24-38. https://doi.org/10.1109/mci.2009.932254
Sims, C. A. (1980). Macroeconomics and Reality. Econometrica, Vol. 48, No. 1 (Jan., 1980), pp. 1-48 (48 pages). https://doi.org/https://doi.org/10.2307/1912017
Sing, M. C. P., Edwards, D. J., Liu, H. J. X., & Love, P. E. D. (2015). Forecasting Private-Sector Construction Works: VAR Model Using Economic Indicators. Journal of Construction Engineering and Management, 141(11). https://doi.org/10.1061/(asce)co.1943-7862.0001016
Sun, Y., Li, J., Liu, J., Chow, C., Sun, B., & Wang, R. (2014). Using causal discovery for feature selection in multivariate numerical time series. Machine Learning, 101(1-3), 377-395. https://doi.org/10.1007/s10994-014-5460-1
Wan, R., Mei, S., Wang, J., Liu, M., & Yang, F. (2019). Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting. Electronics, 8(8). https://doi.org/10.3390/electronics8080876
Wang, C.-H., & Chen, J.-Y. (2019). Demand forecasting and financial estimation considering the interactive dynamics of semiconductor supply-chain companies. Computers & Industrial Engineering, 138. https://doi.org/10.1016/j.cie.2019.106104
Wu, J. M.-T., Sun, L., Srivastava, G., & Lin, J. C.-W. (2021). A long short-term memory network stock price prediction with leading indicators. Big Data, 9(5), 343-357.
Zhang, L., Bian, W., Qu, W., Tuo, L., & Wang, Y. (2021). Time series forecast of sales volume based on XGBoost. Journal of Physics: Conference Series,