Deep learning improves reliable time series uncertainty estimates
Conformal Prediction for Time Series with Deep Sequence Models
Machine Learning
Summary
It can be hard to know how confident to be about predictions from data that changes over time, like weather or stock prices. The authors studied ways to use special types of deep learning models that look at sequences to better estimate uncertainty in these predictions. They explored three techniques and showed mathematically that these methods can give trustworthy uncertainty ranges under certain conditions. They also tested their ideas on real-world data and found that combining deep sequence models with uncertainty methods works well.
What this means in practice
- •For financial analysts: Produce reliable prediction intervals for stock price forecasts that realistically account for uncertainty over time.
- •For energy demand planners: Generate trustworthy uncertainty estimates for future electricity demand predictions using deep sequence models.
Authors
Junghwan Lee, Jonghyeok Lee, Yao Xie
Abstract
Recent advances in deep learning for time series prediction have amplified the need for reliable uncertainty quantification. Conformal prediction has gained attention as a distribution-free framework for constructing prediction intervals with coverage guarantees. However, its coverage guarantees rely on data exchangeability, an assumption generally violated in time series. Active research has focused on developing conformal prediction methods for time series that overcome this limitation. While deep sequence models, such as recurrent neural networks and Transformers, have often been used in conformal prediction for time series, limited work has systematically studied how deep sequence models can be utilized in conformal prediction for time series. In this work, we systematically investigate the use of deep sequence models in conformal prediction for time series through three approaches: conditional quantile regression, conditional quantile function estimation, and localized conformal prediction. We provide a theoretical analysis establishing asymptotic conditional coverage guarantees for all three approaches under suitable assumptions. Through comprehensive experiments on real-world datasets, we demonstrate the effectiveness of leveraging deep sequence models into conformal prediction for time series.