Prediction of economic indicators by using extended answer-in-weights neural network

For time-series data prediction, we have investigated a neural network of answer-in-weights (AIW) structure. For more accurate prediction, we proposed to use an AIW network consisting of three component estimators. And we have considered about input functions of AIW neural networks. In this paper, we propose extended AIW neural networks of 2-steps structure. To confirm the effectiveness of the proposed method, we make computer simulation using actual economic indicators.