Surrogate uncertainty estimation for your time series forecasting black-box: learn when to trust

TL;DR

This paper presents a computationally efficient surrogate Gaussian process method for estimating uncertainty in time series forecasts, improving confidence interval accuracy across various models and datasets.

Contribution

It introduces a black-box surrogate Gaussian process approach that enhances any base model with reliable uncertainty estimates without heavy computational costs.

Findings

Outperforms bootstrap and built-in methods in accuracy

Effective across diverse base models including neural networks and ARIMA

Provides better confidence intervals in medium-data regimes

Abstract

Machine learning models play a vital role in time series forecasting. These models, however, often overlook an important element: point uncertainty estimates. Incorporating these estimates is crucial for effective risk management, informed model selection, and decision-making.To address this issue, our research introduces a method for uncertainty estimation. We employ a surrogate Gaussian process regression model. It enhances any base regression model with reasonable uncertainty estimates. This approach stands out for its computational efficiency. It only necessitates training one supplementary surrogate and avoids any data-specific assumptions. Furthermore, this method for work requires only the presence of the base model as a black box and its respective training data. The effectiveness of our approach is supported by experimental results. Using various time-series forecasting data, we found that our surrogate model-based technique delivers significantly more accurate confidence intervals. These techniques outperform both bootstrap-based and built-in methods in a medium-data regime. This superiority holds across a range of base model types, including a linear regression, ARIMA, gradient boosting and a neural network.