Towards stock market data mining using enriched random forests from textual resources and technical indicators

Manolis Maragoudakis, Dimitrios Serpanos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

The present paper deals with a special Random Forest Data Mining technique, designed to alleviate the significant issue of high dimensionality in volatile and complex domains, such as stock market prediction. Since it has been widely acceptable that media affect the behavior of investors, information from both technical analysis as well as textual data from various on-line financial news resources are considered. Different experiments are carried out to evaluate different aspects of the problem, returning satisfactory results. The results show that the trading strategies guided by the proposed data mining approach generate higher profits than the buy-and-hold strategy, as well as those guided by the level-estimation based forecasts of standard linear regression models and other machine learning classifiers such as Support Vector Machines, ordinary Random Forests and Neural Networks.

Original languageEnglish
Title of host publicationIFIP Advances in Information and Communication Technology
Pages278-286
Number of pages9
Volume339 AICT
DOIs
Publication statusPublished - 25 Nov 2010
Externally publishedYes
Event6th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2010 - Larnaca, Cyprus
Duration: 6 Oct 20107 Oct 2010

Publication series

NameIFIP Advances in Information and Communication Technology
Volume339 AICT
ISSN (Print)18684238

Other

Other6th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2010
CountryCyprus
CityLarnaca
Period6/10/107/10/10

Fingerprint

Market data
Data mining
Resources
Stock market
Technical analysis
News
Support vector machine
Classifier
Machine learning
Investors
Neural networks
Linear regression model
Profit
Dimensionality
Experiment
Trading strategies
Prediction

Keywords

  • Data mining
  • Expert systems
  • Markov blanket
  • Random forests
  • Stock return forecasting
  • Trading strategies

ASJC Scopus subject areas

  • Information Systems and Management

Cite this

Maragoudakis, M., & Serpanos, D. (2010). Towards stock market data mining using enriched random forests from textual resources and technical indicators. In IFIP Advances in Information and Communication Technology (Vol. 339 AICT, pp. 278-286). (IFIP Advances in Information and Communication Technology; Vol. 339 AICT). https://doi.org/10.1007/978-3-642-16239-8_37

Towards stock market data mining using enriched random forests from textual resources and technical indicators. / Maragoudakis, Manolis; Serpanos, Dimitrios.

IFIP Advances in Information and Communication Technology. Vol. 339 AICT 2010. p. 278-286 (IFIP Advances in Information and Communication Technology; Vol. 339 AICT).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Maragoudakis, M & Serpanos, D 2010, Towards stock market data mining using enriched random forests from textual resources and technical indicators. in IFIP Advances in Information and Communication Technology. vol. 339 AICT, IFIP Advances in Information and Communication Technology, vol. 339 AICT, pp. 278-286, 6th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2010, Larnaca, Cyprus, 6/10/10. https://doi.org/10.1007/978-3-642-16239-8_37
Maragoudakis M, Serpanos D. Towards stock market data mining using enriched random forests from textual resources and technical indicators. In IFIP Advances in Information and Communication Technology. Vol. 339 AICT. 2010. p. 278-286. (IFIP Advances in Information and Communication Technology). https://doi.org/10.1007/978-3-642-16239-8_37
Maragoudakis, Manolis ; Serpanos, Dimitrios. / Towards stock market data mining using enriched random forests from textual resources and technical indicators. IFIP Advances in Information and Communication Technology. Vol. 339 AICT 2010. pp. 278-286 (IFIP Advances in Information and Communication Technology).
@inproceedings{5ab133ef5e994e4fbf20b4cd1bce64e5,
title = "Towards stock market data mining using enriched random forests from textual resources and technical indicators",
abstract = "The present paper deals with a special Random Forest Data Mining technique, designed to alleviate the significant issue of high dimensionality in volatile and complex domains, such as stock market prediction. Since it has been widely acceptable that media affect the behavior of investors, information from both technical analysis as well as textual data from various on-line financial news resources are considered. Different experiments are carried out to evaluate different aspects of the problem, returning satisfactory results. The results show that the trading strategies guided by the proposed data mining approach generate higher profits than the buy-and-hold strategy, as well as those guided by the level-estimation based forecasts of standard linear regression models and other machine learning classifiers such as Support Vector Machines, ordinary Random Forests and Neural Networks.",
keywords = "Data mining, Expert systems, Markov blanket, Random forests, Stock return forecasting, Trading strategies",
author = "Manolis Maragoudakis and Dimitrios Serpanos",
year = "2010",
month = "11",
day = "25",
doi = "10.1007/978-3-642-16239-8_37",
language = "English",
isbn = "364216238X",
volume = "339 AICT",
series = "IFIP Advances in Information and Communication Technology",
pages = "278--286",
booktitle = "IFIP Advances in Information and Communication Technology",

}

TY - GEN

T1 - Towards stock market data mining using enriched random forests from textual resources and technical indicators

AU - Maragoudakis, Manolis

AU - Serpanos, Dimitrios

PY - 2010/11/25

Y1 - 2010/11/25

N2 - The present paper deals with a special Random Forest Data Mining technique, designed to alleviate the significant issue of high dimensionality in volatile and complex domains, such as stock market prediction. Since it has been widely acceptable that media affect the behavior of investors, information from both technical analysis as well as textual data from various on-line financial news resources are considered. Different experiments are carried out to evaluate different aspects of the problem, returning satisfactory results. The results show that the trading strategies guided by the proposed data mining approach generate higher profits than the buy-and-hold strategy, as well as those guided by the level-estimation based forecasts of standard linear regression models and other machine learning classifiers such as Support Vector Machines, ordinary Random Forests and Neural Networks.

AB - The present paper deals with a special Random Forest Data Mining technique, designed to alleviate the significant issue of high dimensionality in volatile and complex domains, such as stock market prediction. Since it has been widely acceptable that media affect the behavior of investors, information from both technical analysis as well as textual data from various on-line financial news resources are considered. Different experiments are carried out to evaluate different aspects of the problem, returning satisfactory results. The results show that the trading strategies guided by the proposed data mining approach generate higher profits than the buy-and-hold strategy, as well as those guided by the level-estimation based forecasts of standard linear regression models and other machine learning classifiers such as Support Vector Machines, ordinary Random Forests and Neural Networks.

KW - Data mining

KW - Expert systems

KW - Markov blanket

KW - Random forests

KW - Stock return forecasting

KW - Trading strategies

UR - http://www.scopus.com/inward/record.url?scp=78549250702&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78549250702&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-16239-8_37

DO - 10.1007/978-3-642-16239-8_37

M3 - Conference contribution

SN - 364216238X

SN - 9783642162381

VL - 339 AICT

T3 - IFIP Advances in Information and Communication Technology

SP - 278

EP - 286

BT - IFIP Advances in Information and Communication Technology

ER -