用tsfresh构造新特征，能显著提升无监督异常检测效果
Unsupervised Feature Construction for Anomaly Detection in Time Series -- An Evaluation
- 用tsfresh从时序数据自动提取统计特征
- 在5个数据集上，Isolation Forest准确率显著提高
- 适合做时序异常检测但缺乏标签数据的场景
为在无先验知识下精准检测时序异常，是直接基于原始时序表示构建检测器，还是使用现有自动变量构造库生成新（表格）表示？本文通过深入实验研究了两种流行检测器（孤立森林和局部离群因子）的表现。结果表明，在5个不同数据集上，使用tsfresh库计算的新表示能使孤立森林性能显著提升。
原文摘要 · Abstract (English)
To detect anomalies with precision and without prior knowledge in time series, is it better to build a detector from the initial temporal representation, or to compute a new (tabular) representation using an existing automatic variable construction library? In this article, we address this question by conducting an in-depth experimental study for two popular detectors (Isolation Forest and Local Outlier Factor). The obtained results, for 5 different datasets, show that the new representation, computed using the tsfresh library, allows Isolation Forest to significantly improve its performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。