No abstract

No abstract

In this paper, we apply the self-organizing multilayer percep tron (SOMLP) architecture proposed by Gas for temporal predic tion. Our main idea is to divide a data series into several small er sub-series which are treated as individual functions or signals.Then we can find the tendencies in detail and perform predictions based on the properties of these signals. By using the SOMLP, sig nals can be clustered and similar sub-series for the underlying pre diction are located. The idea is tested by forecasting the Taiwan S tock Exchange Capitalization Weighted Stock Index (TAIEX) and results are presented.