Parallel distributed processing: explorations in the microstructure of cognition, vol. 2: psychological and biological models
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Forecasting S&P 500 stock index futures with a hybrid AI system
Decision Support Systems
On the momentum term in gradient descent learning algorithms
Neural Networks
Designing personalized intelligent financial decision support systems
Decision Support Systems
Information complexity of neural networks
Neural Networks
A framework for applying intelligent agents to support electronic trading
Decision Support Systems
Hi-index | 0.00 |
The recent research escalation in the area of neural networks in business is due to the fact that the underlying structures and associated functions controlling business data are generally unknown. Neural networks offer a class of tools that can approximate financial patterns to a satisfactory degree of accuracy. The vast majority of relevant studies rely on a gradient algorithm, typically a variation of the backpropagation one.This paper uses the feed forward backpropagation (FBP) algorithm in order to improve the topology of predictive neural network for finance. It also identifies the most significant parameters of the training and the optimisation procedures and compares the performance of different back propagation feed forward neural networks' topologies. We show that an appropriate selection of the training parameters ensures convergence of the (FBP) and can be used for predictions in intelligent trading.