Text mining of news-headlines for FOREX market prediction: A Multi-layer Dimension Reduction Algorithm with semantics and sentiment

•FOREX prediction through text mining of news is viable and effective.•Feature-selection by abstraction of word-hypernyms increases prediction accuracy.•Feature-weighting based on the sum of pos and neg sentiment scores is effective.•Feature-reduction based on maximum optimization for prediction-tar...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Expert systems with applications Ročník 42; číslo 1; s. 306 - 324
Hlavní autoři:	Khadjeh Nassirtoussi, Arman, Aghabozorgi, Saeed, Ying Wah, Teh, Ngo, David Chek Ling
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Amsterdam Elsevier Ltd 01.01.2015 Elsevier
Témata:	Algorithms Applied sciences Artificial intelligence Breaking Computer science; control theory; systems Decision theory. Utility theory Exact sciences and technology Exchange Expert systems FOREX prediction Information systems. Data bases Market prediction Market sentiment analysis Markets Memory organisation. Data processing Multilayers News mining News semantic analysis Operational research and scientific management Operational research. Management science Portfolio theory Semantics Software Speech and sound recognition and synthesis. Linguistics Texts Market prediction FOREX prediction News mining Market sentiment analysis News semantic analysis Noise reduction Layer model Data mining Modeling Relevance Motivation Semantics News Sparse matrix Selection criterion Dynamic model Exchange rate Textual data Data analysis Dimensionality Integration Filtration Knowledge representation Financial market Text Market survey Abstraction Noise control Data reduction Social decision Dimension reduction Monetary market Heuristic method Foreign currency Prediction market Algorithm analysis Press
ISSN:	0957-4174, 1873-6793
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!