Experimental Investigation of Forecasting Methods Based on Universal Measures

2011/04/12 by Boris Ryabko, Ryabko, Boris, Pavel Pristavka +1
Computer Science · Decision Sciences · Economics, Econometrics and Finance · Mathematics · Physics and Astronomy · #Complex Systems and Time Series Analysis #Forecasting Techniques and Applications #Stock Market Forecasting Methods #cs.IT #math.IT #physics.data-an

paper · pdf · doi:10.48550/arxiv.1104.2239

submitted

arxiv created 2011/04/12 · arxiv updated 2011/04/13

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.

Related

• Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible
• Application of data compression techniques to time series forecasting
• Compression-based methods for nonparametric density estimation, on-line prediction, regression and classification for time series
• Principles and Algorithms for Forecasting Groups of Time Series:\n Locality and Globality
• Some examples of application for predicting of compressive sensing method