集成直接多步预测方法及其在宏观经济和金融数据上的比较研究
Ensembled Direct Multi-Step forecasting methodology with comparison on macroeconomic and financial data
AI总结：
提出集成直接多步（EDMS）预测方法，结合集成与直接多步技术，在宏观经济和金融数据上平均提升预测性能33.32%，有时超过60%。
摘要：
对宏观经济和金融数据（如GDP、CPI、失业率和股票指数）的准确预测对于国家、企业和投资者的成功至关重要，因此对可靠预测模型的需求持续存在。本研究提出了一种新颖的时间序列预测方法，将集成技术与直接多步（DMS）预测程序相结合。这种集成直接多步（EDMS）方法不仅利用了两种技术的优势，还充分发挥了它们的协同作用。方法中的集成模型根据性能、复杂度和计算资源需求进行选择，涵盖了从简单线性和多项式回归到中等复杂度的ETS以及复杂的LSTM模型的全部模型复杂度范围。模型根据其性能进行加权。在DMS程序中，我们将重新训练限制为经济和金融数据分别对应的一年和五年（月）预测。对于其他预测范围，采用标准的迭代多步（IMS）程序，从而有效降低计算需求，同时保持令人满意的结果。所提出的方法与通常应用于IMS生成预测的集成技术进行了基准比较，使用了多个公开可用的宏观经济和金融数据集。结果表明，EDMS方法带来了显著的性能提升，在分析的数据集上平均提升33.32%，有时提升幅度超过60%。
英文摘要：
Accurate forecasts of macroeconomic and financial data, such as GDP, CPI, unemployment rates, and stock indices, are crucial for the success of countries, businesses, and investors, resulting in a constant demand for reliable forecasting models. This research introduces a novel methodology for time series forecasting that combines Ensemble technique with a Direct Multi-Step (DMS) forecasting procedure. This Ensembled Direct Multi-Step (EDMS) approach not only leverages the strengths of both techniques but also capitalizes on their synergy. The ensemble models in the methodology were selected based on performance, complexity, and computational resource requirements, encompassing a full spectrum of model complexities, from simple Linear and Polynomial Regression to medium-complexity ETS and complex LSTM model. Models were weighted based on their performances. In the DMS procedure we limit retraining to one- and five- year/month forecasts for economic and financial data respectively. Standard Iterative Multi-Step (IMS) procedure is employed for other horizons, effectively reducing computational demands while maintaining satisfactory results. The proposed methodology is benchmarked against Ensemble technique conventionally applied to IMS-generated forecasts, utilizing several publicly available macroeconomic and financial datasets. Results demonstrate a significant performance improvement with EDMS methodology, averaging a 33.32% enhancement across the analysed datasets, and sometimes improvement reaching above 60%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
