Fully Automated Correlated Time Series Forecasting in Minutes

TL;DR

This paper introduces a fully automated, efficient framework for correlated time series forecasting that automatically searches and trains models in minutes, outperforming existing methods in accuracy and speed.

Contribution

The paper presents a novel automated forecasting framework that automatically prunes search spaces, identifies optimal models via zero-shot search, and accelerates training, addressing key limitations of prior methods.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Significantly reduces search and training time to minutes.

Demonstrates robustness across multiple real-world datasets.

Abstract

Societal and industrial infrastructures and systems increasingly leverage sensors that emit correlated time series. Forecasting of future values of such time series based on recorded historical values has important benefits. Automatically designed models achieve higher accuracy than manually designed models. Given a forecasting task, which includes a dataset and a forecasting horizon, automated design methods automatically search for an optimal forecasting model for the task in a manually designed search space, and then train the identified model using the dataset to enable the forecasting. Existing automated methods face three challenges. First, the search space is constructed by human experts, rending the methods only semi-automated and yielding search spaces prone to subjective biases. Second, it is time consuming to search for an optimal model. Third, training the identified model for a new task is also costly. These challenges limit the practicability of automated methods in real-world settings. To contend with the challenges, we propose a fully automated and highly efficient correlated time series forecasting framework where the search and training can be done in minutes. The framework includes a data-driven, iterative strategy to automatically prune a large search space to obtain a high-quality search space for a new forecasting task. It includes a zero-shot search strategy to efficiently identify the optimal model in the customized search space. And it includes a fast parameter adaptation strategy to accelerate the training of the identified model. Experiments on seven benchmark datasets offer evidence that the framework is capable of state-of-the-art accuracy and is much more efficient than existing methods.