 |
    |
Evolutionary Ensemble for Stock Prediction
Yung-Keun Kwon and Byung-Ro Moon
School of Computer Science & Engineering, Seoul National University, Shilim-dong, Kwanak-gu, Seoul, 151-742 Koreakwon@soar.snu.ac.kr
moon@soar.snu.ac.kr
Abstract. We propose a genetic ensemble of recurrent neural networks for stock prediction model. The genetic algorithm tunes neural networks in a two-dimensional and parallel framework. The ensemble makes the decision of buying or selling more conservative. It showed notable improvement on the average over not only the buy-and-hold strategy but also other traditional ensemble approaches.
LNCS 3103, p. 1102 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004