A New Macro-Economic Time-Series Forecasting Using Linear Genetic Programming Algorithm for Electrical Capacitance Tomography
Roberto Sánchez, Javier Martinez, Benjamı́n Barán · 2008
Recent studies in financial economics suggest that good technical analysis may have a merit in data series prediction.Linear Genetic Programming (LGP) is a genetic programming variant that evolves sequences of instructions from an imperative programming language.This paper presents a LGP approach to search times series forecasting rules.Results for three Paraguayan macro-economic time series (Consumer Price Index, Gross Internal Product & Paraguayan import from Argentina) and one artificial time series indicate that these prediction rules may be more accurate to forecast future values than some standard statistical models in use.