Evolving least squares support vector machines for stock market trend mining
IEEE Transactions on Evolutionary Computation - Special issue on computational finance and economics
Multistage neural network metalearning with application to foreign exchange rates forecasting
MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
Hi-index | 0.00 |
In this study, a novel adaptive learning algorithm for feed-forward network based on optimized instantaneous learning rates is proposed to predict stock market movements. In this new algorithm, the optimized adaptive learning rates are used to adjust the weight changes dynamically. For illustration and testing purposes the proposed algorithm is applied to two main stock price indices: S&P 500 and Nikkei 225. The experimental results reveal that the proposed algorithm provides a promising alternative to stock market prediction.