Detecting anomalous subsequences in time series is an important task in time series analytics because it serves the identification of special events, such as production faults, delivery bottlenecks, system defects, or heart flicker. Consequently, many algorithms have been developed for the automatic detection of such anomalous patterns. The enormous number of approaches (i. e., more than 158 as of today), the lack of properly labeled test data, and the complexity of time series anomaly benchmarking have, though, led to a situation where choosing the best detection technique for a given anomaly detection task is a difficult challenge. In this demonstration, we present TimeEval, an extensible, scalable and automatic benchmarking toolkit for time series anomaly detection algorithms. TimeEval includes an extensive data generator and supports both interactive and batch evaluation scenarios. With our novel toolkit, we aim to ease the evaluation effort and help the community to provide more meaningful evaluations.

The automated detection of sequential anomalies in time series is an essential task for many applications, such as the monitoring of technical systems, fraud detection in high-frequency trading, or the early detection of disease symptoms. All these applications require the detection to findallsequential anomalies possiblyfaston potentially verylargetime series. In other words, the detection needs to be effective, efficient and scalable w.r.t. the input size. Series2Graph is an effective solution based on graph embeddings that are robust against re-occurring anomalies and can discover sequential anomalies of arbitrary length and works without training data. Yet, Series2Graph is no t scalable due to its single-threaded approach; it cannot, in particular, process arbitrarily large sequences due to the memory constraints of a single machine. In this paper, we propose our distributed anomaly detection system, short DADS, which is an efficient and scalable adaptation of Series2Graph. Based on the actor programming model, DADS distributes the input time sequence, intermediate state and the computation to all processors of a cluster in a way that minimizes communication costs and synchronization barriers. Our evaluation shows that DADS is orders of magnitude faster than S2G, scales almost linearly with the number of processors in the cluster and can process much larger input sequences due to its scale-out property.

Clustering is an effective, unsupervised classification approach for time series analysis applications that suffer a natural lack of training data. One such application is the development of jet engines, which involves numerous test runs and failure detection processes. While effective data mining algorithms exist for the detection of anomalous and structurally conspicuous test recordings, these algorithms do not perform any semantic labeling. So, data analysts spend many hours connecting the large amounts of automatically extracted observations to their underlying root causes. The complexity, number, and variety of extracted time series make this task hard not only for humans, but also for existing time series clustering algorithms. These algorithms either require training data for supervised learning, cannot deal with varying time series lengths, or suffer from exceptionally long runtimes. In this paper, we propose JET, an unsupervised, highly efficient clustering algorithm for large numbers of variable-lengths time series. The main idea is to transform the input time series into a metric space, then apply a very fast conventional clustering algorithm to obtain effective but rather coarse-grained pre-clustering of the data; this pre-clustering serves to subsequently estimate the more accurate but also more costly shape-based distances of the time series and, thus, enables JET to apply a highly effective hierarchical clustering algorithm to the entire input time series collection. Our experiments demonstrate that JET is highly accurate and much faster than its competitors.