Adaptive Conformal Inference for Multi-Step Ahead Time-Series Forecasting Online
This work addresses the need for reliable uncertainty quantification in time-series forecasting for applications requiring sequential predictions, though it is incremental as it extends an existing method to multi-step scenarios.
The paper tackles the problem of providing finite-sample coverage guarantees for multi-step ahead time-series forecasting in an online setting by adapting the adaptive conformal inference (ACI) algorithm. The result is a method that maintains coverage guarantees at each prediction step and overall, as demonstrated through numerical examples with variable target error and learning rates.
The aim of this paper is to propose an adaptation of the well known adaptive conformal inference (ACI) algorithm to achieve finite-sample coverage guarantees in multi-step ahead time-series forecasting in the online setting. ACI dynamically adjusts significance levels, and comes with finite-sample guarantees on coverage, even for non-exchangeable data. Our multi-step ahead ACI procedure inherits these guarantees at each prediction step, as well as for the overall error rate. The multi-step ahead ACI algorithm can be used with different target error and learning rates at different prediction steps, which is illustrated in our numerical examples, where we employ a version of the confromalised ridge regression algorithm, adapted to multi-input multi-output forecasting. The examples serve to show how the method works in practice, illustrating the effect of variable target error and learning rates for different prediction steps, which suggests that a balance may be struck between efficiency (interval width) and coverage.t