Algorithmic Information Forecastability
Information Theory
2023-12-04 v2 Artificial Intelligence
math.IT
Abstract
The outcome of all time series cannot be forecast, e.g. the flipping of a fair coin. Others, like the repeated {01} sequence {010101...} can be forecast exactly. Algorithmic information theory can provide a measure of forecastability that lies between these extremes. The degree of forecastability is a function of only the data. For prediction (or classification) of labeled data, we propose three categories for forecastability: oracle forecastability for predictions that are always exact, precise forecastability for errors up to a bound, and probabilistic forecastability for any other predictions. Examples are given in each case.
Cite
@article{arxiv.2304.10752,
title = {Algorithmic Information Forecastability},
author = {Glauco Amigo and Daniel Andrés Díaz-Pachón and Robert J. Marks and Charles Baylis},
journal= {arXiv preprint arXiv:2304.10752},
year = {2023}
}