Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series

By Kasun Bandara, Christoph Bergmeir, Slawek Smyl. 2017

32 citations recorded by the source corpus.

With the advent of Big Data, nowadays in many applications databases containing large quantities of similar time series are available. Forecasting time series in these domains with traditional univariate forecasting procedures leaves great potentials for producing accurate forecasts untapped. Recurrent neural networks, and in particular Long Short-Term Memory (LSTM) networks have proven recently that they are able to outperform state-of-the-art univariate time series forecasting methods in this context, when trained across all available time series. However, if the time series database is heterogeneous accuracy may degenerate, so that on the way towards fully automatic forecasting methods in this space, a notion of similarity between the time series needs to be built into the methods. To this end, we present a prediction model using LSTMs on subgroups of similar time series, which are identified by time series clustering techniques. The proposed methodology is able to consistently outperform the baseline LSTM model, and it achieves competitive results on benchmarking datasets, in particular outperforming all other methods on the CIF2016 dataset.

Subfields: Model Architectures, Time-Series & Forecasting

How researchers see this paper

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

In Model Architectures

In Time-Series & Forecasting

Citations in the corpus

Probabilistic Forecasting with Spline Quantile Function RNNs (2019, background): “, 2008) have been complemented increasingly by deep learning-based techniques that can learn complex patterns across time series and make use of rich metadata without significant manual feature engineering effort (Flunkert et al., 2017; Mukherjee et al., 2018; Qin et al., 2017; Smyl et al., 2018; Ba”
Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, background): “[14] RNN + Classical Decomposition Point ≥ 1 sMAPE CIF2016, NN5 Clusters time series based on set of features and train one model per cluster”
catch22: CAnonical Time-series CHaracteristics (2019, background): “Selecting a subset of features from thousands of candidate features is computationally expensive, making the highly-comparative approach unfeasible for some real-world applications, especially those involving large training datasets [5,27,7].”