VAEneu: A New Avenue for VAE Application on Probabilistic Forecasting

TL;DR

VAEneu introduces a novel autoregressive VAE-based approach for multistep univariate probabilistic time series forecasting, optimizing the CRPS loss to produce sharp, calibrated predictive distributions with superior performance.

Contribution

This paper presents VAEneu, a new autoregressive VAE framework optimized with CRPS for improved probabilistic forecasting accuracy.

Findings

VAEneu outperforms 12 baseline models across 12 datasets.

The method produces well-calibrated and sharp predictive distributions.

Extensive benchmarking demonstrates its superior forecasting performance.

Abstract

This paper presents VAEneu, an innovative autoregressive method for multistep ahead univariate probabilistic time series forecasting. We employ the conditional VAE framework and optimize the lower bound of the predictive distribution likelihood function by adopting the Continuous Ranked Probability Score (CRPS), a strictly proper scoring rule, as the loss function. This novel pipeline results in forecasting sharp and well-calibrated predictive distribution. Through a comprehensive empirical study, VAEneu is rigorously benchmarked against 12 baseline models across 12 datasets. The results unequivocally demonstrate VAEneu's remarkable forecasting performance. VAEneu provides a valuable tool for quantifying future uncertainties, and our extensive empirical study lays the foundation for future comparative studies for univariate multistep ahead probabilistic forecasting.