Forecasting Big Time Series: Old and New

By Christos Faloutsos, Jan Gasthaus, Tim Januschowski, Bernie Wang. 2018

74 citations recorded by the source corpus.

Time series forecasting is a key ingredient in the automation and optimization of business processes: in retail, deciding which products to order and where to store them depends on the forecasts of future demand in different regions; in cloud computing, the estimated future usage of services and infrastructure components guides capacity planning; and workforce scheduling in warehouses, call centers, factories requires forecasts of the future workload. Recent years have witnessed a paradigm shift in forecasting techniques and applications, from computer-assisted model- and assumption-based to data-driven and fully-automated. This shift can be attributed to the availability of large, rich, and diverse time series data sources, posing unprecedented challenges to traditional time series forecasting methods. As such, how can we build statistical models to efficiently and effectively learn to forecast from large and diverse data sources? How can we leverage the statistical power of "similar" time series to improve forecasts in the case of limited observations? What are the implications for building forecasting systems that can handle large data volumes? The objective of this tutorial is to provide a concise and intuitive overview of the most important methods and tools available for solving large-scale forecasting problems. We review the state of the art in three related fields: (1) classical modeling of time series, (2) scalable tensor methods, and (3) deep learning for forecasting. Further, we share lessons learned from building scalable forecasting systems. While our focus is on providing an intuitive overview of the methods and practical issues, we also present technical details underlying these powerful tools.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, 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

In Electrical and Electronic Engineering

In Signal Processing

Citations in the corpus

Deep Factors for Forecasting (2019, methodology): “To assess the performance of our algorithm, we compare with DeepAR ( DA ), a state-of-art RNN-based probabilistic forecasting algorithm on the publicly available AWS SageMaker (Januschowski et al., 2018), MQ-RNN ( MR ), a sequence model that generates conditional predictive quantiles (Wen et al., 20”
Bayesian Temporal Factorization for Multidimensional Time Series Prediction (2019, methodology): “ons. Making predictions on these time series, such as forecasting urban trafﬁc states and regional air quality, serves as a foundation to many real-world applications and beneﬁts many scientiﬁc ﬁelds [1], [2]. For example, predicting the demand and states (e.g., speed, ﬂow) of urban trafﬁc is essent”
Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, background): “, see a series of recent tutorials [56, 55, 57, 58]).”
GluonTS: Probabilistic Time Series Models in Python (2019, background): “Further distinctions within the subspace of discriminative models are discussed in more detail in (Faloutsos et al., 2018).”