Numerous deep learning architectures have been developed to accommodate the diversity
of time-series datasets across different domains. In this article, we survey common encoder …

Deep learning based forecasting methods have become the methods of choice in many
applications of time series prediction or forecasting often outperforming other approaches …

Although we have witnessed great success of pre-trained models in natural language
processing (NLP) and computer vision (CV), limited progress has been made for general …

Multi-horizon forecasting often contains a complex mix of inputs–including static (ie time-
invariant) covariates, known future inputs, and other exogenous time series that are only …

Real-world time-series datasets are often multivariate with complex dynamics. To capture
this complexity, high capacity architectures like recurrent-or attention-based sequential deep …

With the increasing importance and complexity of data pipelines, data quality became one of
the key challenges in modern software applications. The importance of data quality has …

Abstract Machine learning is a powerful tool for gleaning knowledge from massive amounts
of data. While a great deal of machine learning research has focused on improving the …

The prevalence of approaches based on gradient boosted trees among the top contestants
in the M5 competition is potentially the most eye-catching result. Tree-based methods out …

Classifying forecasting methods as being either of a “machine learning” or “statistical” nature
has become commonplace in parts of the forecasting literature and community, as …

Producing probabilistic forecasts for large collections of similar and/or dependent time series
is a practically highly relevant, yet challenging task. Classical time series models fail to …