Experimental Investigation of Forecasting Methods Based on Universal Measures

TL;DR

This paper explores a new forecasting method for stationary and ergodic processes using universal measures, demonstrating improved prediction accuracy on geophysical and economic time series compared to existing methods.

Contribution

Introduces a novel forecasting approach based on universal measures and empirically validates its superior performance on real-world time series data.

Findings

Higher prediction accuracy than known methods

Effective on geophysical and economic data

Validates universal measures for forecasting

Abstract

We describe and experimentally investigate a method to construct forecasting algorithms for stationary and ergodic processes based on universal measures (or so-called universal data compressors). Using some geophysical and economical time series as examples, we show that the precision of thus obtained predictions is higher than that of known methods.