Rule discovery and matching in stock databases

You Min Ha, Sang Wook Kim, Sang Hyun Park, Jung Im Won, Jee Hee Yoon

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

2 Citations (Scopus)

Abstract

This paper addresses an approach that recommends investment types to stock investors by discovering useful rules from past changing patterns of stock prices in databases. First, we define a new rule model for recommending stock investment types. For a frequent pattern of stock prices, if its subsequent stock prices are matched to a condition of an investor, the model recommends a corresponding investment type for this stock. The frequent pattern is regarded as a rule head, and the subsequent part a rule body. We observed that the conditions on rule bodies are quite different depending on dispositions of investors while rule heads are independent of characteristics of investors in most cases. With this observation, we propose a new method that discovers and stores only the rule heads rather than the whole rules in a rule discovery process. This allows investors to impose various conditions on rule bodies flexibly, and also improves the performance of a rule discovery process by reducing the number of rules to be discovered. For efficient discovery and matching of rules, we propose methods for discovering frequent patterns, constructing a frequent pattern base, and its indexing. We also suggest a method that finds the rules matched to a query from a frequent pattern base, and a method that recommends an investment type by using the rules. Finally, we verify the effectiveness and the efficiency of our approach through extensive experiments with real-life stock data.

Original languageEnglish
Title of host publicationProceedings - 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008
Pages192-198
Number of pages7
DOIs
Publication statusPublished - 2008 Sep 25
Event32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008 - Turku, Finland
Duration: 2008 Jul 282008 Aug 1

Publication series

NameProceedings - International Computer Software and Applications Conference
ISSN (Print)0730-3157

Other

Other32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008
CountryFinland
CityTurku
Period08/7/2808/8/1

Fingerprint

Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications

Cite this

Ha, Y. M., Kim, S. W., Park, S. H., Won, J. I., & Yoon, J. H. (2008). Rule discovery and matching in stock databases. In Proceedings - 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008 (pp. 192-198). [4591556] (Proceedings - International Computer Software and Applications Conference). https://doi.org/10.1109/COMPSAC.2008.20
Ha, You Min ; Kim, Sang Wook ; Park, Sang Hyun ; Won, Jung Im ; Yoon, Jee Hee. / Rule discovery and matching in stock databases. Proceedings - 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008. 2008. pp. 192-198 (Proceedings - International Computer Software and Applications Conference).
@inproceedings{262f37687f3943c6b4581039ce7b43ad,
title = "Rule discovery and matching in stock databases",
abstract = "This paper addresses an approach that recommends investment types to stock investors by discovering useful rules from past changing patterns of stock prices in databases. First, we define a new rule model for recommending stock investment types. For a frequent pattern of stock prices, if its subsequent stock prices are matched to a condition of an investor, the model recommends a corresponding investment type for this stock. The frequent pattern is regarded as a rule head, and the subsequent part a rule body. We observed that the conditions on rule bodies are quite different depending on dispositions of investors while rule heads are independent of characteristics of investors in most cases. With this observation, we propose a new method that discovers and stores only the rule heads rather than the whole rules in a rule discovery process. This allows investors to impose various conditions on rule bodies flexibly, and also improves the performance of a rule discovery process by reducing the number of rules to be discovered. For efficient discovery and matching of rules, we propose methods for discovering frequent patterns, constructing a frequent pattern base, and its indexing. We also suggest a method that finds the rules matched to a query from a frequent pattern base, and a method that recommends an investment type by using the rules. Finally, we verify the effectiveness and the efficiency of our approach through extensive experiments with real-life stock data.",
author = "Ha, {You Min} and Kim, {Sang Wook} and Park, {Sang Hyun} and Won, {Jung Im} and Yoon, {Jee Hee}",
year = "2008",
month = "9",
day = "25",
doi = "10.1109/COMPSAC.2008.20",
language = "English",
isbn = "9780769532622",
series = "Proceedings - International Computer Software and Applications Conference",
pages = "192--198",
booktitle = "Proceedings - 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008",

}

Ha, YM, Kim, SW, Park, SH, Won, JI & Yoon, JH 2008, Rule discovery and matching in stock databases. in Proceedings - 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008., 4591556, Proceedings - International Computer Software and Applications Conference, pp. 192-198, 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008, Turku, Finland, 08/7/28. https://doi.org/10.1109/COMPSAC.2008.20

Rule discovery and matching in stock databases. / Ha, You Min; Kim, Sang Wook; Park, Sang Hyun; Won, Jung Im; Yoon, Jee Hee.

Proceedings - 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008. 2008. p. 192-198 4591556 (Proceedings - International Computer Software and Applications Conference).

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

TY - GEN

T1 - Rule discovery and matching in stock databases

AU - Ha, You Min

AU - Kim, Sang Wook

AU - Park, Sang Hyun

AU - Won, Jung Im

AU - Yoon, Jee Hee

PY - 2008/9/25

Y1 - 2008/9/25

N2 - This paper addresses an approach that recommends investment types to stock investors by discovering useful rules from past changing patterns of stock prices in databases. First, we define a new rule model for recommending stock investment types. For a frequent pattern of stock prices, if its subsequent stock prices are matched to a condition of an investor, the model recommends a corresponding investment type for this stock. The frequent pattern is regarded as a rule head, and the subsequent part a rule body. We observed that the conditions on rule bodies are quite different depending on dispositions of investors while rule heads are independent of characteristics of investors in most cases. With this observation, we propose a new method that discovers and stores only the rule heads rather than the whole rules in a rule discovery process. This allows investors to impose various conditions on rule bodies flexibly, and also improves the performance of a rule discovery process by reducing the number of rules to be discovered. For efficient discovery and matching of rules, we propose methods for discovering frequent patterns, constructing a frequent pattern base, and its indexing. We also suggest a method that finds the rules matched to a query from a frequent pattern base, and a method that recommends an investment type by using the rules. Finally, we verify the effectiveness and the efficiency of our approach through extensive experiments with real-life stock data.

AB - This paper addresses an approach that recommends investment types to stock investors by discovering useful rules from past changing patterns of stock prices in databases. First, we define a new rule model for recommending stock investment types. For a frequent pattern of stock prices, if its subsequent stock prices are matched to a condition of an investor, the model recommends a corresponding investment type for this stock. The frequent pattern is regarded as a rule head, and the subsequent part a rule body. We observed that the conditions on rule bodies are quite different depending on dispositions of investors while rule heads are independent of characteristics of investors in most cases. With this observation, we propose a new method that discovers and stores only the rule heads rather than the whole rules in a rule discovery process. This allows investors to impose various conditions on rule bodies flexibly, and also improves the performance of a rule discovery process by reducing the number of rules to be discovered. For efficient discovery and matching of rules, we propose methods for discovering frequent patterns, constructing a frequent pattern base, and its indexing. We also suggest a method that finds the rules matched to a query from a frequent pattern base, and a method that recommends an investment type by using the rules. Finally, we verify the effectiveness and the efficiency of our approach through extensive experiments with real-life stock data.

UR - http://www.scopus.com/inward/record.url?scp=52149114865&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52149114865&partnerID=8YFLogxK

U2 - 10.1109/COMPSAC.2008.20

DO - 10.1109/COMPSAC.2008.20

M3 - Conference contribution

AN - SCOPUS:52149114865

SN - 9780769532622

T3 - Proceedings - International Computer Software and Applications Conference

SP - 192

EP - 198

BT - Proceedings - 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008

ER -

Ha YM, Kim SW, Park SH, Won JI, Yoon JH. Rule discovery and matching in stock databases. In Proceedings - 32nd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2008. 2008. p. 192-198. 4591556. (Proceedings - International Computer Software and Applications Conference). https://doi.org/10.1109/COMPSAC.2008.20