Large-Scale Unusual Time Series Detection

By Rob J Hyndman, Earo Wang, Nikolay Pavlovich Laptev. 2015

203 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Economics and Econometrics, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Slawek Smyl
2. Jan Gasthaus
3. Tim Januschowski
4. Bernie Wang
5. K. Smith‐Miles
6. Christoph Bergmeir
7. Kasun Bandara
8. Yanfei Kang

In Economics and Econometrics

1. Christoph Bergmeir
2. Kasun Bandara
3. Slawek Smyl
4. K. Smith‐Miles
5. Yanfei Kang
6. Rob J Hyndman
7. Nikolay Pavlovich Laptev
8. Laurent Callot

In Signal Processing

1. Bernie Wang
2. Tim Januschowski
3. Christoph Bergmeir
4. Jan Gasthaus
5. Kasun Bandara
6. Rob J Hyndman
7. Yanfei Kang
8. Slawek Smyl

Citations in the corpus

• Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, methodology): “s seems not practical for our purpose, and limiting the amount of features is desirable, in our proposed framework we follow the second approach, and use a set of selfdescribable features proposed by Hyndman et al. (2015b) to obtain a meaningful division of clusters. These suggested features are des”
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, methodology): “For this reason, the authors propose to cluster the time series according to a vector of features extracted using the technique from [87] and the Snob clustering algorithm [186].”
• Time-series Extreme Event Forecasting with Neural Networks at Uber (2017, background): “(a) Classical time-series features that are manually derived (Hyndman et al., 2015).”
• Visualising forecasting algorithm performance using time series instance spaces (2017, methodology): “…characterising a time series as a feature vector is not new, and has been used for classifying time series (Nanopoulos, Alcock, and Manolopoulos, 2001), clustering time series (Wang, Smith, and Hyndman, 2006), and for identifying outlying or anomalous time series (Hyndman, Wang, and Laptev, 2015).”
• A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting (2020, unknown): “It was only after the end of the competition that a promising R package called tsfeatures came to my attention (Hyndman, Wang, & Laptev, 2015; Kang, Hyndman, & Smith-Miles, 2017).”