Abstract

Three networks are compared for low false alarm stock trend predictions. Short-term trends, particularly attractive for neural network analysis, can be used profitably in scenarios such as option trading, but only with significant risk. Therefore, we focus on limiting false alarms, which improves the risk/reward ratio by preventing losses. To predict stock trends, we exploit time delay, recurrent, and probabilistic neural networks (TDNN, RNN, and PNN, respectively), utilizing conjugate gradient and multistream extended Kalman filter training for TDNN and RNN. We also discuss different predictability analysis techniques and perform an analysis of predictability based on a history of daily closing price. Our results indicate that all the networks are feasible, the primary preference being one of convenience

Department(s)

Electrical and Computer Engineering

Second Department

Computer Science

Keywords and Phrases

Kalman Filters; Conjugate Gradient Methods; Conjugate Gradient Training; Daily Closing Price; Feedforward Neural Nets; Filtering Theory; Forecasting Theory; Learning (Artificial Intelligence); Low False Alarm; Multilayer Perceptrons; Multistream Extended Kalman Filter Training; Nonlinear Filters; Option Trading; Predictability Analysis Techniques; Probabilistic Neural Networks; Recurrent Neural Nets; Recurrent Neural Networks; Risk/Reward Ratio; Short-Term Trends; Stock Markets; Stock Trend Prediction; Time Delay Neural Networks; Time Series

International Standard Serial Number (ISSN)

1045-9227

Document Type

Article - Journal

Document Version

Final Version

File Type

text

Language(s)

English

Rights

© 1998 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link

Share

 
COinS