Transformer Conformal Prediction for Time Series
This work addresses uncertainty estimation for time series forecasting, which is crucial for applications like finance and climate modeling, but it appears incremental as it adapts an existing architecture to a specific task.
The paper tackles the problem of uncertainty quantification in time series forecasting by proposing a Transformer-based conformal prediction method that captures long-range dependencies to estimate prediction intervals, achieving superior performance over existing state-of-the-art methods in experiments with simulated and real data.
We present a conformal prediction method for time series using the Transformer architecture to capture long-memory and long-range dependencies. Specifically, we use the Transformer decoder as a conditional quantile estimator to predict the quantiles of prediction residuals, which are used to estimate the prediction interval. We hypothesize that the Transformer decoder benefits the estimation of the prediction interval by learning temporal dependencies across past prediction residuals. Our comprehensive experiments using simulated and real data empirically demonstrate the superiority of the proposed method compared to the existing state-of-the-art conformal prediction methods.