|
Title:
|
TEXT MINING SYSTEMS FOR PREDICTING MARKET RESPONSE TO NEWS |
|
Author(s):
|
Marc-andré Mittermayer , Gerhard F. Knolmayer |
|
ISBN:
|
978-972-8924-40-9 |
|
Editors:
|
Jörg Roth, Jairo Gutiérrez and Ajith P. Abraham (series editors: Piet Kommers, Pedro Isaías and Nian-Shing Chen) |
|
Year:
|
2007 |
|
Edition:
|
Single |
|
Keywords:
|
Text Mining; Text Categorization; Forecasting; Financial Markets; Performance Evaluation; Comparison of Systems. |
|
Type:
|
Short Paper |
|
First Page:
|
164 |
|
Last Page:
|
169 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Over the last 10 years, several prototypes for predicting the short-term market reactions to news based on text mining
techniques have been developed. Thus far no detailed comparison of the systems and their performance is available. This
paper describes the main systems developed to forecast price trends and presents a framework for comparing the approaches.
The prototypes differ in the text mining methods applied and the data sets used for performance evaluation.
Some (mostly implicit) assumptions of these evaluations are rather unrealistic with respect to properties of financial markets
and the simulated performance results cannot be achieved in reality. Best performance results are obtained with
NewsCATS and we summarize main differences between earlier prototypes and this system. |
|
|
|
|
|
|
