Demonstrates a system that combines a neural network approach with an expert system to provide superior performance compared to either approach alone. Learning capability is provided in a software-based approach to commodity trading systems. The authors used the backpropagation network with some parameters selected experimentally. They used a human expert to implicitly define patterns, using hindsight, that an intelligent system might have been able to use for an accurate prediction. Desired outputs were found by a combination of observing the behavior of technical indices that normally precede a certain kind of market behavior, and by observing the actual market behavior in retrospect. Thus, the network learns to give signals based on data that look favorable to a human expert. The authors show the results of a rule-based daily trading system that has been augmented by a neural network market predictor.
K. Bergerson and D. C. Wunsch, "A Commodity Trading Model Based on a Neural Network-Expert System Hybrid," Proceedings of the International Joint Conference on Neural Networks, 1991., IJCNN-91-Seattle, Institute of Electrical and Electronics Engineers (IEEE), Jan 1991.
The definitive version is available at https://doi.org/10.1109/IJCNN.1991.155192
International Joint Conference on Neural Networks, 1991., IJCNN-91-Seattle
Electrical and Computer Engineering
Keywords and Phrases
Accurate Prediction; Backpropagation Network; Commodity Trading; Commodity Trading Model; Expert Systems; Financial Data Processing; Learning Capability; Market Behavior; Neural Nets; Neural Network-Expert System Hybrid; Performance; Rule-Based Daily Trading System; Software-Based Approach; Technical Indices
Article - Conference proceedings
© 1991 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
01 Jan 1991