NeuroVe$t Journal, Vol. 4 No. 6, November 1996.
Abstract
Quantitative data are today largely processed by computer programs based on traditional or artificial intelligence techniques including statistics, neural networks, genetic algorithms, etc. Conversely, little progress has been made for the processing of qualitative information, which is mainly represented by financial articles from on-line news agencies or from financial newspapers. As a result, financial operators nowadays suffer from qualitative data-overload. This article describes the importance of qualitative information in the financial operators’ investment decision-making process and how natural language processing can be successfully used for processing and analysing such information. The paper focuses on information extraction which can identify specific kinds of information in a source article, producing a list of relevant templates or summaries of the original text. Information extraction can significantly reduce the qualitative data-overload from which traders, brokers, fund managers etc. suffer. The templates produced can be used for a “meta-analysis” of the effects of news on price behaviour. Finally, Natural Language Processing is briefly compared to other artificial intelligence techniques which are widely employed in finance: Neural Networks and Expert Systems.
How to cite
Marco Costantino, Russell J. Collingham, Richard G. Morgan (1996). Qualitative Information in Finance: Natural Language Processing and Information Extraction. NeuroVe$t Journal, Vol. 4 No. 6, November 1996.
BibTeX entry for reference managers (EndNote, Zotero, Mendeley)
@article{costantino1996qualitative,
title = {Qualitative Information in Finance: Natural Language Processing and Information Extraction},
author = {Marco Costantino and Russell J. Collingham and Richard G. Morgan},
year = {1996},
journal = {NeuroVe$t Journal},
volume = {4},
number = {6},
url = {https://www.advanced-finance.com/paper-qualitative-information-in-finance-nlp.html}
}