Forecasting with Leading Economic Indicators—A Neural Network Approach

By Timotej Jagric

Dr. Timotej Jagric works as an assistant in the department for Quantitative Economic Analysis, Faculty of Economics and Business, the University of Maribor in Slovenia. His main research areas are operations research and econometrics. He is a member of the Institute for Economic Analysis and Forecasting and an adviser for the Institute of Macroeconomic Analysis and Development of the Republic of Slovenia.

Despite its obvious importance, short-run prediction of business cycles continues to be a difficult task with limited success in economic analysis. Recent developments, however, suggest that there is scope for adding extensions to the methodology of forecasting major economic fluctuations. In this paper, the author tries to develop a new model that would outperform the forecast accuracy of the classical National Bureau of Economic Research (NBER) leading indicators model. The use of artificial neural networks is proposed here. The main findings are that, at the twelve-month forecasting horizon, improved forecast accuracy could be achieved for in- and out-ofsample data.

This research was supported by the National Science Foundation Grant V5-0540-03-05 and a grant from the CERGE-EI Foundation under a program of the Global Development Network. Additional funds for grantees in the Balkan countries have been provided by the Austrian government through WIIW, Vienna. All opinions expressed are those of the author and have not been endorsed by CERGE-EI, WIIW, or the GDN.

Read the article: HTML | PDF