Robust Predictions with Ambiguous Time Delays: A Bootstrap Strategy

TL;DR

This paper introduces TSMB, a bootstrap framework that effectively manages uncertain and varying time delays in multivariate time series data, enhancing predictive accuracy in complex, dynamic environments.

Contribution

The paper presents a novel nonparametric bootstrap approach, TSMB, for modeling time series with ambiguous or non-deterministic delays, surpassing traditional fixed-delay methods.

Findings

TSMB improves prediction accuracy in delayed time series.

It effectively handles non-constant and uncertain delays.

The framework is versatile for diverse dynamic environments.

Abstract

In contemporary data-driven environments, the generation and processing of multivariate time series data is an omnipresent challenge, often complicated by time delays between different time series. These delays, originating from a multitude of sources like varying data transmission dynamics, sensor interferences, and environmental changes, introduce significant complexities. Traditional Time Delay Estimation methods, which typically assume a fixed constant time delay, may not fully capture these variabilities, compromising the precision of predictive models in diverse settings. To address this issue, we introduce the Time Series Model Bootstrap (TSMB), a versatile framework designed to handle potentially varying or even nondeterministic time delays in time series modeling. Contrary to traditional approaches that hinge on the assumption of a single, consistent time delay, TSMB adopts a nonparametric stance, acknowledging and incorporating time delay uncertainties. TSMB significantly bolsters the performance of models that are trained and make predictions using this framework, making it highly suitable for a wide range of dynamic and interconnected data environments.