Evolutionary Ensemble for Stock Prediction

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.

• Type: Conference
• Year: 2004
• Where: GECCO
• Authors: Yung-Keun Kwon, Byung Ro Moon
• Keywords: GECCO 2004, Neural Networks, Recurrent Neural Networks, Tunes Neural Networks