Using a neural network to forecast inflation

Abstract

Forecasting inflation is a major concern for economists and businessmen. Most researchers have relied upon statistical techniques with their stringent data assumptions and low accuracy rates to predict changes in inflation, but only a few have investigated how neural networks can improve forecasts. Here, we show the results of Consumer Price Index (CPI) forecasts from an artificial neural network using leading economic indicator data in the USA. Results show that the neural network predicts the level of the CPI with a high degree of accuracy.

Citation

Aiken, M. (1999), "Using a neural network to forecast inflation", Industrial Management & Data Systems, Vol. 99 No. 7, pp. 296-301. https://doi.org/10.1108/02635579910291984