CONTEXT SENSITIVITY WITH NEURAL NETWORKS IN FINANCIAL DECISION PROCESSES

Charles Wong and Massimiliano Versace

Global Journal of Business Research, 2011, vol. 5, issue 5, 27-43

Abstract: Context modifies the influence of any trading indicator. Ceteris paribus, a buyer would be more cautious buying in a selling market context than in a buying market. In order for automated, adaptive systems like neural networks to better emulate and assist human decision-making, they need to be context sensitive. Most prior research applying neural networks to trading decision support systems neglected to extract contextual cues, rendering the systems blind to market conditions. This paper explores the theoretical development and quantitative evaluation of context sensitivity in a novel fast learning neural network architecture, Echo ARTMAP. The simulated risk and cost adjusted trading results compare very favorably on a 10-year, random stock study against the market random walk, regression, auto-regression, and multiple neural network models typically used in prior studies. By combining human trader techniques with biologically inspired neural network models, Echo ARTMAP may represent a new tool with which to assist in financial decision-making and to explore life-like context sensitivity.

Keywords: Recurrent neural networks; context sensitivity; financial forecasting; investment decisions (search for similar items in EconPapers)
JEL-codes: G11 G17 (search for similar items in EconPapers)
Date: 2011
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.theibfr2.com/REPEc/ibf/gjbres/gjbr-v5n5-2011/GJBR-V5N5-2011-3.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ibf:gjbres:v:5:y:2011:i:5:p:27-43

Access Statistics for this article

Global Journal of Business Research is currently edited by Terrance Jalbert

More articles in Global Journal of Business Research from The Institute for Business and Finance Research
Bibliographic data for series maintained by Mercedes Jalbert ( this e-mail address is bad, please contact ).