本研究想了解的是預測單變數失業率資料的模型比較，分別是以季節性差分整合移動平均自迴歸模型(SARIMA)、長短期記憶網絡(LSTM)與時序卷積網絡(TCN)在失業率不同期數後，預測上的變化。以樣本外預測的均方根誤差比較預測能力的好壞，雙時序卷積網絡優於SARIMA模型與長短期記憶網絡，而雙時序卷積網絡與SARIMA模型是以迭代方式預測，長短期記憶網絡則是直接預測。失業率的資料先以虛擬變數的方式，去除結構改變的影響。

In order to know about the model predictive ability of unemployment in Taiwan, we try seasonal autoregressive integrated moving average (SARIMA) model, Long Short Term Memory (LSTM) model and also Temporal Convolutional Networks (TCN) model to compare the predictive ability among different forecast horizons. Using out-of-sample root mean square error (RMSE) to check the predictive ability, and then we find double TCN is better than SARIMA model and LSTM model. Double TCN model and SARIMA model use indirect forecasting but LSTM model uses direct forecasting. Besides, we remove the structural impact on unemployment rate data via adding dummy variables.

誌謝 i
中文摘要 ii
英文摘要 iii
表目錄 vi
圖目錄 vii
第一章研究動機1
第二章文獻回顧2
第三章資料5
3.1 台灣失業率趨勢圖. . . . . . . . . . . . . . . . . . . . . . . 5
3.2 類神經網絡的資料標準化. . . . . . . . . . . . . . . . . . . . 6
第四章方法7
4.1 單根與結構性檢定. . . . . . . . . . . . . . . . . . . . . . . 7
4.2 以迴歸移除結構性斷裂點的效果. . . . . . . . . . . . . . . . 10
4.3 挑選最佳的具結構斷裂的季節性差分整合移動平均自迴歸
模型. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
4.4 檢定殘差是否有非線性. . . . . . . . . . . . . . . . . . . . . 13
4.5 簡介類神經網絡. . . . . . . . . . . . . . . . . . . . . . . . . 15
4.6 長短期記憶網絡. . . . . . . . . . . . . . . . . . . . . . . . . 16
4.7 時序卷積網絡. . . . . . . . . . . . . . . . . . . . . . . . . . 19
第五章預測結果比較26
5.1 比較具結構斷裂的季節性差分整合移動平均自迴歸模型、
類神經網絡的樣本外預測的均方根誤差. . . . . . . . . . . . 28
5.2 類神經網絡的訓練狀況. . . . . . . . . . . . . . . . . . . . . 29
第六章結論32
參考資料34

Alla, S., & Adari, S. K. (2019). Beginning Anomaly Detection Using
Python-Based Deep Learning. Springer.
Bai, J., & Perron, P. (2003). Computation and analysis of multiple structural
change models. Journal of Applied Econometrics, 18(1), 1–22.
Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of
generic convolutional and recurrent networks for sequence modeling. arXiv
Preprint arXiv:1803.01271.
Boot, T., & Pick, A. (2020). Does modeling a structural break improve
forecast accuracy? Journal of Econometrics, 215(1), 35–59.
Burnham, K. P., & Anderson, D. R. (2004). Multimodel Inference: Understanding
AIC and BIC in Model Selection. Sociological Methods & Research,
33(2), 261–304.
Coulombe, P. G., Leroux, M., Stevanovic, D., & Surprenant, S.
(2020). How is Machine Learning Useful for Macroeconomic Forecasting?
arXiv:2008.12477 [Econ, Stat].
Dauphin, Y. N., Fan, A., Auli, M., & Grangier, D. (2017). Language Modeling
with Gated Convolutional Networks. arXiv:1612.08083 [Cs].
Diebold, F. X. (1998). The Past, Present, and Future of Macroeconomic
Forecasting. Journal of Economic Perspectives, 12(2), 175–192.
Dritsaki, C. (2016). Forecast of Sarima Models: Αn Application to Unemployment
Rates of Greece. American Journal of Applied Mathematics and
Statistics, 4(5), 136–148.
Elliott, G., & Timmermann, A. (2008). Economic Forecasting. Journal of
Economic Literature, 46(1), 3–56.
Hall, A. S., & Cook, T. R. (2017). Macroeconomic Indicator Forecasting
with Deep Neural Networks. Federal Reserve Bank of Kansas City.
Hansen, B. E. (2001). The New Econometrics of Structural Change: Dating
Breaks in U.S. Labour Productivity. Journal of Economic Perspectives,
15(4), 117–128.
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for
Image Recognition. arXiv:1512.03385 [Cs].
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory.
Neural Computation, 9(8), 1735–1780.
Hyndman, R. J., & Khandakar, Y. (2008). Automatic Time Series Forecasting:
The forecast Package for R. Journal of Statistical Software, 27(1),
1–22.
Kuan, C.-M., & White, H. (1994). Artificial neural networks: An econometric
perspective. Econometric Reviews, 13(1), 1–91.
Layard, R., Nickell, S., & Jackman, R. (1991). Unemployment: Macroeconomic
Performance and the Labour Market. Oxford University Press.
Lee, T. H., White, H., & Granger, C. (1993). Testing for neglected nonlinearity
in time series models: A comparison of neural network methods and
alternative tests. Journal of Econometrics, 56(3), 269–290.
Lucas, R. E. (1976). Econometric policy evaluation: A critique. Carnegie-
Rochester Conference Series on Public Policy, 1, 19–46.
Merity, S., Keskar, N. S., & Socher, R. (2017). Regularizing and Optimizing
LSTM Language Models. arXiv:1708.02182 [Cs].
Montgomery, A. L., Zarnowitz, V., Tsay, R. S., & Tiao, G. C. (1998). Forecasting
the U.S. Unemployment Rate. Journal of the American Statistical Association,
93(442), 478–493. https://doi.org/10.2307/2670094
Nair, V., & Hinton, G. E. (2010). Rectified Linear Units Improve Restricted
Boltzmann Machines. In.
Oord, A. van den, Dieleman, S., Zen, H., Simonyan, K., Vinyals, O.,
Graves, A., … Kavukcuoglu, K. (2016). WaveNet: A Generative Model for
Raw Audio. arXiv:1609.03499 [Cs].
Salimans, T., & Kingma, D. P. (2016). Weight Normalization: A Simple
Reparameterization to Accelerate Training of Deep Neural Networks.
arXiv:1602.07868 [Cs].
Stock, J., & Watson, M. (1999). Cointegration, Causality and Forecasting:
A Festschrift for Clive W.J. Granger. Oxford: Oxford University Press.
Swanson, N., & White, H. (1997). A Model Selection Approach To Real-
Time Macroeconomic Forecasting Using Linear Models And Artificial Neural
Networks. The Review of Economics and Statistics, 79(4), 540–550.
Teräsvirta, T., Lin, C.-F., & Granger, C. W. J. (1993). Power of the Neural
Network Linearity Test. Journal of Time Series Analysis, 14(2), 209–220.
US Census Bureau, B. C. M. (2017). X-13ARIMA-SEATS Seasonal Adjustment
Program. US Census Bureau. Retrieved from https://www.census.
gov/srd/www/x13as/
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. J. (1989).
Phoneme recognition using time-delay neural networks. IEEE Transactions on
Acoustics, Speech, and Signal Processing.
Wei, W. W. S. (2005). Time Series Analysis : Univariate and Multivariate
Methods. Boston.
Zeileis, A., Kleiber, C., Krämer, W., & Hornik, K. (2003). Testing and
Dating of Structural Changes in Practice. Computational Statistics & Data
Analysis, 44, 109–123.
Zhu, X., & Wu, X. (2004). Class Noise vs. Attribute Noise: A Quantitative
Study. Artificial Intelligence Review.
Zivot, E., & Andrews, D. W. K. (1992). Further Evidence on the Great
Crash, the Oil-Price Shock, and the Unit-Root Hypothesis. Journal of Business
& Economic Statistics, 10(3), 251–270.