A genetic algorithm based nonlinear grey Bernoulli model for output forecasting in integrated circuit industry

In this article, an improved nonlinear grey Bernoulli model by using genetic algorithms to solve the optimal parameter estimation problem of small amount of data used in the forecast is proposed. The time series data of Taiwan’s integrated circuit industry (1990–2007) was used as the test data set. In addition, the mean absolute percentage error and the root mean square percentage error were used to compare the performance of the forecast models. The results showed that the improved nonlinear grey Bernoulli model is more accurate and performs better than the traditional GM(1,1) model and grey Verhulst model. Moreover, the optimum mechanisms indeed improve the grey model of prediction accuracy by using genetic algorithms approach.