Driver Identification and PCA Augmented Selection Shrinkage Framework for Nordic System Price Forecasting
北欧电力系统价格预测：驱动因素识别与 PCA 增强的选择收缩框架AI 解读 ↓
← 返回论文列表与筛选
阅读说明
本页整理公开书目信息，不生成学术质量评分。AI 解读根据题名及所注明的摘要或原文片段生成，未完成全文核验，可能有误；具体假设、证明与结论请核对原文。摘要保留来源文本，未经模型改写。
DOI 首次登记不等于接收或发表日期。部分更正、评论等条目没有独立摘要；缺少可靠材料时保留待补状态。
本页为预印本版本；arXiv 收录、作者填写的期刊信息以及作者既有发表经历，都不单独证明本篇已接收。作者发表记录按 OpenAlex 身份与完整姓名、本站覆盖期刊 ISSN 及正式卷期核对，只展示已核实例，档案仍可能误合并。
引用量采用 OpenAlex 单条关联记录，不合计多个记录；关联记录可能包含正式发表版本，不等于此版本单独引用。缺失不视为零，引用指标不代表论文质量。
关注作者按书目中的完整姓名匹配，同名和姓名变体需人工辨别。相关论文先按共享细分方向和具体方法排列，再参考通用方法与发表日期。
分类依据与纠错
AI 根据所提供的论文材料归类：摘要核心是电力价格的时间序列建模与预测组合；金融对冲背景本身不足以归入资产定价。
反馈分类问题
正在核对关联版本…
代码、数据与补充材料
正在核对对应版本的资源…
北欧电力系统价格预测：驱动因素识别与 PCA 增强的选择收缩框架
- 研究问题
- 如何识别北欧电力系统价格的主要驱动因素，并结合降维与预测组合，在保持可解释性的同时改善价格预测？
- 方法与思路
- 作者结合 K-means、多重季节趋势分解和 SARIMA 进行特征工程，再以 PCA 降维，并按组合层面的偏差方差权衡筛选和加权预测。
- 材料陈述的贡献
- 摘要称历史电力市场数据中的组合预测优于输入模型、TFT 及若干常用组合方法，同时保持与输入模型相近的计算成本。
- 阅读关注点
- 应核对预测期与样本划分、特征工程和 PCA 是否仅用训练信息，以及组合权重、显著性检验与计算成本的比较口径。
- 阅读边界
- 这是 arXiv 预印本，同行评审与期刊接收未经核实；摘要未提供预测误差、时期与检验细节，不能据此确认跨市场优势。
原文摘要
The System Price (SP) of the Nordic electricity market serves as a key reference for financial hedge contracts such as Electricity Price Area Differentials (EPADs) and other risk management instruments. Therefore, the identification of drivers and the accurate forecasting of SP are essential for market participants to design effective hedging strategies. This paper develops a systematic framework that combines interpretable drivers analysis with robust forecasting methods. It proposes an interpretable feature engineering algorithm to identify the main drivers of the Nordic SP based on a novel combination of K-means clustering, Multiple Seasonal-Trend Decomposition (MSTD), and Seasonal Autoregressive Integrated Moving Average (SARIMA) model. Then, it applies principal component analysis (PCA) to the identified data matrix, which is adapted to the downstream task of price forecasting to mitigate the issue of imperfect multicollinearity in the data. Finally, we propose a multi-forecast selection-shrinkage algorithm for Nordic SP forecasting, which selects a subset of complementary forecast models based on their bias-variance tradeoff at the ensemble level and then computes the optimal weights for the retained forecast models to minimize the error variance of the combined forecast. Using historical data from the Nordic electricity market, we demonstrate that the proposed approach outperforms individual input models uniformly, robustly, and significantly, while maintaining a comparable computational cost. Notably, our systematic framework produces superior results using simple input models, outperforming the state-of-the-art Temporal Fusion Transformer (TFT). Furthermore, we show that our approach also exceeds the performance of several well-established practical forecast combination methods.