Holt-Winters 法是一種可以同時考慮線性趨勢以及季節性的指數平滑法， 對於單一週期性時間序列資料有不錯的預測效果。Taylor [12] 提出的雙季節 指數平滑法比 Holt-Winters 法多了一個季節影響，適合用在具有兩種週期性 的資料。另外，指數平滑法雖然簡易好用，但是並無機率模型。Hyndman et al. [6] 將指數平滑法表示成具有單一誤差來源的狀態空間模型。有了狀態 空間模型表示式, 便能寫出概似函數，進行參數估計及區間估計, 而且可以 很自然地新增外生變數於此模型中。然而，對於單一誤差的狀態空間模型， 目前文獻上並無討論如何以類似卡爾曼濾波器的方式，來進行狀態的更新。
本研究的主要貢獻有兩點。首先是關於指數平滑法在來店人數預測的比 較。本論文使用美國服飾業的來店人數資料，我們發現該筆資料具有雙季 節性，使用 Taylor [12] 的雙季節指數平滑法，在預測上明顯優於單季節指 數平滑法。第二點貢獻是針對單一誤差的狀態空間模型，目前文獻上的更 新預測步驟，仍是延續原本的指數平滑法，本論文試著提出類似卡爾曼濾 波器的迭代更新法，來進行狀態更新。有了這種更新方法後，處理外生變 數就容易許多

[1] S. Tom Au, Guang-Qin Ma, and Shu-Ngai Yeung. Automatic forecasting of double seasonal time series with applications on mobility network traffic prediction. 2011.

[2] Robert Goodell Brown. Statistical forecasting for inventory control. McGraw Hill, New York, 1959.

[3] Phillip G Gould, Anne B Koehler, J. Keith Ord, Ralph D Snyder, Rob J Hyndman, and Farshid Vahid-Araghi. Forecasting time series with multiple seasonal patterns. European Journal of Operational Research, 2008.

[4] Charles C Holt. Forecasting seasonals and trends by exponentially weighted moving averages. Carnegie Institute of Technology, Graduate school of Industrial Administration, 1957.

[5] Rob J Hyndman and Yeasmin Khandakar. Automatic time series forecasting: the forecast package for R. Journal of Statistical Software, 26(3):1–22, 2008.

[6] Rob J. Hyndman, Anne B. Koehler, J. Keith Ord, and Ralph D. Snyder. Forecasting with Exponential Smoothing:The State Space Approach. Springer, 2008.

[7] Mohamed A. Ismail, Alyaa R. Zahran, and Eman M. Abd El-Metaal. Forecasting hourly electricity demand in egypt using double seasonal autoregressive integrated moving average model. 2015.

[8] R. E. Kalman. A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 82:35–45, 1960.

[9] R. E. Kalman and R. S. Bucy. New results in linear filtering and new results in linear filtering and prediction theory. Journal of Basic Engineering, 83:95–108, 1961.

[10] Reinaldo Castro Souza, Mônica Barros, and Cristina Vidigal C. de Miranda. Short term load forecasting using double seasonal exponential smoothing and interventions to account for holidays and temperature effects. 2007.

[11] Ivan Svetunkov. smooth: Forecasting Using Smoothing Functions, 2018.

[12] J. W. Taylor. Short-term electricity demand forecasting using double seasonal exponential smoothing. The Journal of the Operational Research Society, 2013.

[13] Greg Welch and Gary Bishop. An introduction to the kalman filter. Technical report, Department of Computer Science University of North Carolina at Chapel Hill, 2006.

[14] Peter R Winters. Forecasting sales by exponentially weighted moving averages. Management Science, 1960.

[15] 施佩吟. 指數平滑模型應用於來店人數預測之研究. 碩, 國立政治大學, 2015.