臺灣景氣狀態之預測

FORECASTING BUSINESS CYCLES IN TAIWAN

蕭宇翔(Yu-Hsiang Hsiao)；林依伶(Yi-Ling Lin)

景氣循環 ； 景氣指標 ； 機器學習 ； Business cycle ； Business indicators ； Machine learning

臺灣經濟預測與政策

51卷1期（2020 / 10 / 01）

1 - 56

繁體中文

國發會認定並發布景氣循環峰谷時點存在一定時間的落後，使施政單位不易即時掌握景氣狀態變化，鑑於近年臺灣經濟成長變動劇烈，本文搜集大量國內、外總體經濟變數，預測2001年以來臺灣景氣狀態變化。除採logistic模型逐一檢視各變數對當期或未來臺灣景氣衰退的預測表現外，亦運用4種能考量大量變數資訊的預測模型：以向前選取法（forward stepwise approach）篩選變數組成多變量logistic模型，運用主成分分析從大量總體變數萃取主要因子，組成logistic因子模型，以及random forest與boosting兩種機器學習演算法，進而比較不同預測模型的樣本外預測表現。根據樣本外預測結果，在向前零期預測（zero-step ahead forecast）方面，採用實質海關出口值單一變數即能有效捕捉當月景氣狀態，而對未來1-6個月的短中期預測時，考量大量變數資訊的機器學習法預測表現普遍較佳，而因子模型對未來1-3個月的預測亦有不錯的表現。

Announcements of the dates of peaks and troughs in business cycles are made with such a considerable lag that policy makers can't know the current business cycle regime early. In this paper, we collect a wide range of domestic and foreign business indicators to assess their abilities to forecast Taiwan's recessions since 2001. We adopt logistic models to examine the usefulness of each indicator and consider four different methods to extract relevant information from all indicators: a forward stepwise approach, a logistic factor model, and two machine learning approaches. The analysis focuses on out-of- sample performance from the current month (zero-step-ahead forecast) to six months ahead. Our empirical results show that the ＂real exports of goods＂ has the best predictive power for zero-step-ahead forecast. However, for one-month- to six-month-ahead forecasts, machine learning techniques show better out-of-sample performance than other forecast models.

1. 陳宜廷, Y.-T.,謝志昇, C.-S.(2006)。臺灣實質國民生產毛額年成長率的狀態變化意涵。經濟論文，34(1)，41-91。
   連結：
2. 陳淑玲, S.-L.,黃裕烈, Y.-L.(2014)。總體變數之領先、同時與落後性質之認定與指標構成項目之選取—LARS 方法的運用。臺灣經濟預測與政策，44(2)，133-170。
   連結：
3. 陳淑玲, S.-L,黃裕烈, Y.-L.(2015)。臺灣景氣基準循環指數之檢討與改進。臺灣經濟預測與政策，46(1)，1-42。
   連結：
4. Berge, T. J.(2015).Predicting Recessions with Leading Indicators: Model Averaging and Selection over the Business Cycle.Journal of Forecasting,34,455-471.
5. Berge, T. J.,Jordà, Ò.(2011).Evaluating the Classification of Economic Activity into Recessions and Expansions.American Economic Journal: Macroeconomics,3(2),246-277.
6. Breiman, L.(2001).Random Forests.Machine Learning,45(1),5-32.
7. Chauvet, M.,Potter, S.(2005).Forecasting Recessions Using the Yield Curve.Journal of Forecasting,24,77-103.
8. Chen, Z.,Iqbal, A.,Lai, H.(2011).Forecasting the Probability of US Recessions: A Probit and Dynamic Factor Modelling Approach.Canadian Journal of Economics,44(2),651-672.
9. Christiansen, C.,Eriksen, J. N.,Møller, S. V.(2014).Forecasting US Recession: The Role of Sentiment.Journal of Banking and Finance,49,459-468.
10. Döpke, J.,Fritsche, U.,Pierdzioch, C.(2017).Predicting Recessions with Boosted Regression Trees.International Journal of Forecasting,33,745-759.
11. Dueker, M.(1997).Strengthening the Case for the Yield Curve as a Predictor of U.S. Recessions.Federal Reserve Bank of St. Louis Review,79,41-51.
12. Estrella, A.(1998).A New Measure of Fit for Equations with Dichotomous Dependent Variables.Journal of Business and Economic Statistics,16(2),198-205.
13. Estrella, A.,Mishkin, F. S.(1998).Predicting U.S. Recessions: Financial Variables as Leading Indicators.Review of Economics and Statistics,80(1),45-61.
14. Fornaro, P.(2016).Forecasting US Recessions with a Large Set of Predictors.Journal of Forecasting,35,477-492.
15. Friedman, J. H.(2001).Greedy Function Approximation: A Gradient Boosting Machine.Annals of Statistics,29(5),1189-1232.
16. Giusto, A.,Piger, J.(2017).Identifying Business Cycle Turning Points in Real Time with Vector Quantization.International Journal of Forecasting,33,174-184.
17. Gogas, P.,Papadimitriou, T.,Matthaiou, M.,Chrysanthidou, E.(2015).Yield Curve and Recession Forecasting in a Machine Learning Framework.Computational Economics,45,635-645.
18. Hamilton, J. D.(2011).Calling Recessions in Real Time.International Journal of Forecasting,27(4),1006-1026.
19. Han, J. W.,Kamber, M.,Pei, J.(2012).Data Mining: Concepts and Techniques.Waltham:Morgan Kaufmann Publishers.
20. Hand, D. J.,Vinciotti, V.(2003).Local versus Global Models for Classification Problems: Fitting Models Where It Matters.American Statistician,57(2),124-131.
21. Hastie, T.,Tibshirani, R.,Friedman, J.(2009).The Elements of Statistical Learning.New York:Springer Inc.
22. Kauppi, H.(2008).Helsinki Center of Economic Research Discussion PaperHelsinki Center of Economic Research Discussion Paper,未出版
23. Kauppi, H.,Saikkonen, P.(2008).Predicting U.S. Recessions with Dynamic Binary Response Models.Review of Economics and Statistics,90(4),777-791.
24. Liu, W.,Moench, E.(2016).What Predicts U.S. Recessions?.International Journal of Forecasting,32(4),1138-1150.
25. Long, P. M.,Servedio, R. A.(2010).Random Classification Noise Defeats All Convex Potential Boosters.Machine Learning,78,287-304.
26. Ng, S.(2014).Viewpoint: Boosting Recessions.Canadian Journal of Economics,47(1),1-34.
27. Nilsson, R. and G. Gyomai (2011), “Cycle Extraction: A Comparison of the Phase-Average Trend Method, the Hodrick-Prescott and Christiano-Fitzgerald Filters,” OECD Statistics Working Paper, No. 2011/04.
28. Nyberg, H.(2010).Dynamic Probit Models and Financial Variables in Recession Forecasting.Journal of Forecasting,29,215-230.
29. Owyang, M. T.,Piger, J.,Wall, H. J.(2015).Forecasting National Recessions Using State-Level Data.Journal of Money, Credit and Banking,47(5),847-866.
30. Proietti, T.(2005).New Algorithms for Dating the Business Cycle.Computational Statistics and Data Analysis,49,477-498.
31. Raffinot, T. (2016), “Investing through Economic Cycles with Ensemble Machine Learning Algorithms,” Working Paper, Université Paris-Dauphine.
32. Raileanu, L. E.,Stoffel, K.(2004).Theoretical Comparison between the Gini Index and Information Gain Criteria.Annals of Mathematics and Artificial Intelligence,41,77-93.
33. Ridgeway, G. (2012), “Generalized Boosted Models: A Guide to the GBM Package,” https://pdfs.semanticscholar.org/a3f6/d964ac323b87d2de3434b23444cb774a216e.pdf.
34. Stock, H. J.,Watson, M. W.(2003).How Did Leading Indicator Forecasts Perform during the 2001 Recession?.FRB Richmond Economic Quarterly,89(3),71-90.
35. Stock, H. J.,Watson, M. W.(2002).Macroeconomic Forecasting Using Diffusion Indexes.Journal of Business and Economic Statistics,20(2),147-162.
36. Ward, F.(2017).Spotting the Danger Zone: Forecasting Financial Crises with Classification Tree Ensembles and Many Predictors.Journal of Applied Econometrics,32(2),359-378.
37. Wright, J.(2006).Federal Reserve Board Finance and Economics Discussion Series Working PaperFederal Reserve Board Finance and Economics Discussion Series Working Paper,未出版
38. 吳懿娟, Y.-J.(2007)。我國殖利率曲線與經濟活動間關係之實證分析。中央銀行季刊，29(3)，23-64。
39. 徐之強, C.-C.,黃裕烈, Y.-L.(2005)。行政院經濟建設委員會委託研究報告行政院經濟建設委員會委託研究報告,未出版
40. 徐之強, C.-C.,葉錦徽, J.-H.(2009)。行政院經濟建設委員會委託研究報告行政院經濟建設委員會委託研究報告,未出版
41. 徐志宏, J.-H.(2012)。臺灣第 12 次景氣循環谷底之認定。經濟研究，12，1-44。
42. 徐志宏, J.-H.(2011)。臺灣景氣指標長期趨勢估計法之研析。經濟研究，11，1-34。
43. 徐志宏, J.-H.,周大森, T.-S.(2010)。近期臺灣景氣循環峰谷之認定。經濟研究，10，1-33。
44. 張志揚, Z.-Y.(2014)。臺灣地區通膨預期與總體變數動態關係之探討。中央銀行季刊，36(4)，51-74。
45. 陳劍虹, C.-H.(2015)。近年臺灣經濟情勢回顧—第 13 次景氣循環谷底初探。經濟研究，15，1-26。
46. 劉欣姿, H.-T.(2013)。領先指標預測能力之研究。經濟研究，13，79-108。

1. 朱浩榜(2021)。即時認定台灣的景氣轉折。經濟論文叢刊，49(3)，335-370。
2. (2024)。大量變數下的高頻率平滑化「台灣景氣指標」。經濟論文叢刊，52(1)，77-118。