本研究應用多種機器學習模型對台灣的消費者物價指數（CPI）、核心消費者物價指數（Core CPI）和生產者物價指數（PPI）進行預測，並比較不同模型在不同預測時間跨度上的性能。使用的模型包括自迴歸模型（AR）、LASSO迴歸模型、彈性網路迴歸模型（EN）、隨機森林（RF）、深度神經網絡（DNN）、循環神經網絡（RNN）以及混合模型（LASSO加彈性網路和彈性網路加隨機森林）。
結果顯示，AR模型在所有預測期內均表現優異，特別是在長期預測中顯示出良好的穩定性和準確性，是短期和長期預測的最佳選擇。RF模型在短期和中期預測中也表現出色，顯示出其強大的預測能力，特別是在處理高維數據和捕捉數據複雜模式方面。LASSO和EN模型在短期預測中表現不佳，但在長期預測中有所改善。DNN和RNN在長期預測中具有一定的潛力，但在短期預測中誤差較高。混合模型在不同預測期內的表現不如單一模型穩定，但在長期預測中有一定改善。

This study applies various machine learning models to forecast Taiwan’s Consumer Price Index (CPI), Core Consumer Price Index (Core CPI), and Producer Price Index (PPI), comparing the performance of different models over various forecast horizons. The models used include Autoregressive (AR), LASSO regression, Elastic Net regression (EN), Random Forest (RF), Deep Neural Network (DNN), Recurrent Neural Network (RNN), and hybrid models (LASSO+Elastic Net and Elastic Net+Random Forest).
The results show that the AR model performs excellently across all forecast horizons, especially in long-term forecasts, demonstrating good stability and accuracy. It is the best choice for both short-term and long-term forecasts. The RF model also performs well in short-term and medium-term forecasts, showing strong predictive capabilities, particularly in handling high-dimensional data and capturing complex patterns in the data. The LASSO and EN models perform poorly in short-term forecasts but improve in long-term forecasts. DNN and RNN exhibit some potential in long-term forecasts but have higher errors in short-term forecasts. Hybrid models are less stable than individual models across different forecast horizons, but they show some improvement in long-term forecasts.

中文文獻
林馨怡、顏佑銘、葉錦徽(2024)，「台灣通膨率預測：運用大數據資料分析」，
中央銀行委託計畫
蕭雲豪(2023)，「台灣水果價格之預測-機器學習之應用」，國立臺灣大學，碩士
論文，14
羅婉蘋(2023)，「通貨膨脹目標機制的政策效果估計：機器學習與模型平均方法
之實證應用」，國立政治大學，碩士論文，19
英文文獻
Baybuza, I. (2018), “Inflation Forecasting Using Machine Learning Methods”,
Russian Journal of Money and Finance, 77(4), pp. 42–59.
Garcia, R., and Johnson, M. (2022),” Potential of Deep Neural Networks in US.
Inflation Forecasting”, Journal of Banking & Finance,947
Hochreiter, S., and Schmidhuber, J. (1997). Long Short-Term Memory. Neural
Computation, 1735–1780.
Ivascu, C. F. (2023),”Can Machine Learning Models Predict. Inflation?” ,
Proceedings. of the International Conference on Business Excellence,1748 - 1756
Kim Y. ,Park J. and Lee H. (2021),”Application of LSTM Models in Forecasting South Korean. Inflation”, Economic Modelling, 3-45
Pavlov, E. (2020),”Forecasting Inflation in Russia Using Neural Networks”,Russian
Journal of Money and Finance, 57–73
Rodríguez-V. A., Sánchez, M., and Jiménez, J. (2020),”Forecasting Costa Rican
inflation with machine learning methods”,Latin American Journal of Central
Banking, 100012
Sharma, A., and Singh, S. (2020),” XGBoost-based Model for Inflation Prediction in
India”, Procedia Computer Science,115
Smith, J. (2017),”Machine Learning Models in Multinational Inflation
Forecasting”,Forecasting Economics,774
Yamada, T., Suzuki, K., and Tanaka, S. (2018),”Elastic Net Model Application in
Japanese Inflation Forecasting”,Energy Economics,37-66
Zhou X., Wang, Y., and Zhang, L. (2019),” Inflation Forecasting with Machine
Learning Methods in China”,Journal of Economic Dynamics and Control,71
Zilberman (2021). Forecasting Inflation in a Data-Rich Environment: The Benefits of
Machine Learning Methods. Journal of Business & Economic Statistics, 98-119