<FONT face=Verdana>As to small size samples which have many characteristic variables

when Partial Least Squares (PLS) principle and structural properties of Elman neural network are taken into account

PLS-Elman is put forward.The new algorithm

when carrying feature reduction on high-dimensional and small size sample

takes its relativity to dependent variable into account.Obtained data carries on network training and simulation

clearly simplifies network structure and can get more precise network models.According to case analysis

the result shows that new algorithm improves convergence rate of the etwork

the predicting precision and proves thatnew algorithm improves the efficiency of the dealing with problems of the network.In the meantime

in order to test the effectiveness of new algorithm

it is compared with Elman neural network algorithm based on Principal Component Analysis (PCA-Elman) and it is observed that PLS-Elman algorithm has more advantages.