A Neural Networks Model of the Venezuelan Economy

TL;DR

This paper proposes a neural network-based model to forecast Venezuela's Monthly Economic Activity General Indicator (IGAEM), aiming to improve economic fluctuation predictions for better policy and investment decisions.

Contribution

It introduces a non-parametric neural network approach to forecast the IGAEM, demonstrating its effectiveness in economic and financial time series prediction.

Findings

Neural network models can effectively forecast the IGAEM.

The approach outperforms traditional parametric methods.

Forecasts can anticipate economic fluctuations with improved accuracy.

Abstract

Besides an indicator of the GDP, the Central Bank of Venezuela generates the so called Monthly Economic Activity General Indicator. The a priori knowledge of this indicator, which represents and sometimes even anticipates the economy's fluctuations, could be helpful in developing public policies and in investment decision making. The purpose of this study is forecasting the IGAEM through non parametric methods, an approach that has proven effective in a wide variety of problems in economics and finance.