Creating Probabilistic Forecasts from Arbitrary Deterministic Forecasts using Conditional Invertible Neural Networks

TL;DR

This paper introduces a novel method using conditional invertible neural networks to convert any deterministic forecast into a probabilistic one, effectively capturing uncertainty without complex assumptions.

Contribution

The paper presents a new approach employing cINNs to generate probabilistic forecasts from arbitrary deterministic forecasts, bypassing traditional statistical assumptions.

Findings

Outperforms traditional uncertainty quantification methods

Achieves better probabilistic forecasts than state-of-the-art benchmarks

Demonstrates mathematical validity of the approach

Abstract

In various applications, probabilistic forecasts are required to quantify the inherent uncertainty associated with the forecast. However, numerous modern forecasting methods are still designed to create deterministic forecasts. Transforming these deterministic forecasts into probabilistic forecasts is often challenging and based on numerous assumptions that may not hold in real-world situations. Therefore, the present article proposes a novel approach for creating probabilistic forecasts from arbitrary deterministic forecasts. In order to implement this approach, we use a conditional Invertible Neural Network (cINN). More specifically, we apply a cINN to learn the underlying distribution of the data and then combine the uncertainty from this distribution with an arbitrary deterministic forecast to generate accurate probabilistic forecasts. Our approach enables the simple creation of probabilistic forecasts without complicated statistical loss functions or further assumptions. Besides showing the mathematical validity of our approach, we empirically show that our approach noticeably outperforms traditional methods for including uncertainty in deterministic forecasts and generally outperforms state-of-the-art probabilistic forecasting benchmarks.