Desempenho econômico-financeiro do setor de papel e celulose brasileiro: testando a influência de variáveis macroeconômicas via redes neurais artificiais.

Abstract

The evaluation of economic, property and financial aspects of the economy can be made through analysis of the Financial-Economic indicators that, when properly forecasted, can bring great benefits to the company and its shareholders. Over the past years, several authors have studied the relationship between these indicators and macroeconomic variables. This paper will investigate, using Neural Networks, the influence of the following variables: GDP, Exchange Rate, Interest Rate and Inflation, over the performance of four Brazilian Pulp and Paper companies: Fibria, Suzano Papel e Celulose Irani and Klabin. For this analysis, two models were applied to the database, one using only the indicators historical data, and another using, in addition to, the macroeconomic variables. According to the evaluation criteria, applied on the period of the study, the performance of the macroeconomic variables were significant to predict the changes of the Financial-Economic index.