The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
La détection des valeurs aberrantes dans un ensemble de données est très importante pour effectuer une exploration de données appropriée. Dans cet article, nous proposons une méthode pour détecter efficacement les valeurs aberrantes en effectuant une analyse de cluster à l'aide de l'algorithme DS amélioré par rapport à l'algorithme k-means. Cette méthode est plus simple à détecter les valeurs aberrantes que les méthodes traditionnelles, et ces valeurs aberrantes détectées peuvent indiquer quantitativement « le degré de valeur aberrante ». Grâce à cette méthode, nous détectons les jours de négociation anormaux des OHLC pour le S&P500 et le FTSA, qui sont des indices boursiers typiques et mondiaux, du début 2005 à la fin de 2015. Ils sont définis comme des jours de négociation non stables, et les conditions car les marchés instables sont exploités comme de nouvelles connaissances. En appliquant les connaissances obtenues aux OHLC du début de 2016 à la fin de 2018, nous pouvons prédire les jours de négociation non stables au cours de cette période. En vérifiant le contenu prédit, nous montrons le fait que les connaissances appropriées ont été exploitées avec succès et montrons l'efficacité de la méthode de détection des valeurs aberrantes proposée dans cet article. De plus, nous référençons mutuellement et analysons de manière comparative les résultats de l’application de cette méthode à plusieurs indices boursiers. Cette analyse permet de visualiser quand et où les impacts sociaux et économiques se produisent et comment ils se propagent à travers la terre. C'est l'une des nouvelles applications utilisant cette méthode.
Hideaki IWATA
Wakayama University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Hideaki IWATA, "Non-Steady Trading Day Detection Based on Stock Index Time-Series Information" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 6, pp. 821-828, June 2020, doi: 10.1587/transfun.2019EAP1151.
Abstract: Outlier detection in a data set is very important in performing proper data mining. In this paper, we propose a method for efficiently detecting outliers by performing cluster analysis using the DS algorithm improved from the k-means algorithm. This method is simpler to detect outliers than traditional methods, and these detected outliers can quantitatively indicate “the degree of outlier”. Using this method, we detect abnormal trading days from OHLCs for S&P500 and FTSA, which are typical and world-wide stock indexes, from the beginning of 2005 to the end of 2015. They are defined as non-steady trading days, and the conditions for becoming the non-steady markets are mined as new knowledge. Applying the mined knowledge to OHLCs from the beginning of 2016 to the end of 2018, we can predict the non-steady trading days during that period. By verifying the predicted content, we show the fact that the appropriate knowledge has been successfully mined and show the effectiveness of the outlier detection method proposed in this paper. Furthermore, we mutually reference and comparatively analyze the results of applying this method to multiple stock indexes. This analyzes possible to visualize when and where social and economic impacts occur and how they propagate through the earth. This is one of the new applications using this method.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2019EAP1151/_p
Copier
@ARTICLE{e103-a_6_821,
author={Hideaki IWATA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Non-Steady Trading Day Detection Based on Stock Index Time-Series Information},
year={2020},
volume={E103-A},
number={6},
pages={821-828},
abstract={Outlier detection in a data set is very important in performing proper data mining. In this paper, we propose a method for efficiently detecting outliers by performing cluster analysis using the DS algorithm improved from the k-means algorithm. This method is simpler to detect outliers than traditional methods, and these detected outliers can quantitatively indicate “the degree of outlier”. Using this method, we detect abnormal trading days from OHLCs for S&P500 and FTSA, which are typical and world-wide stock indexes, from the beginning of 2005 to the end of 2015. They are defined as non-steady trading days, and the conditions for becoming the non-steady markets are mined as new knowledge. Applying the mined knowledge to OHLCs from the beginning of 2016 to the end of 2018, we can predict the non-steady trading days during that period. By verifying the predicted content, we show the fact that the appropriate knowledge has been successfully mined and show the effectiveness of the outlier detection method proposed in this paper. Furthermore, we mutually reference and comparatively analyze the results of applying this method to multiple stock indexes. This analyzes possible to visualize when and where social and economic impacts occur and how they propagate through the earth. This is one of the new applications using this method.},
keywords={},
doi={10.1587/transfun.2019EAP1151},
ISSN={1745-1337},
month={June},}
Copier
TY - JOUR
TI - Non-Steady Trading Day Detection Based on Stock Index Time-Series Information
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 821
EP - 828
AU - Hideaki IWATA
PY - 2020
DO - 10.1587/transfun.2019EAP1151
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2020
AB - Outlier detection in a data set is very important in performing proper data mining. In this paper, we propose a method for efficiently detecting outliers by performing cluster analysis using the DS algorithm improved from the k-means algorithm. This method is simpler to detect outliers than traditional methods, and these detected outliers can quantitatively indicate “the degree of outlier”. Using this method, we detect abnormal trading days from OHLCs for S&P500 and FTSA, which are typical and world-wide stock indexes, from the beginning of 2005 to the end of 2015. They are defined as non-steady trading days, and the conditions for becoming the non-steady markets are mined as new knowledge. Applying the mined knowledge to OHLCs from the beginning of 2016 to the end of 2018, we can predict the non-steady trading days during that period. By verifying the predicted content, we show the fact that the appropriate knowledge has been successfully mined and show the effectiveness of the outlier detection method proposed in this paper. Furthermore, we mutually reference and comparatively analyze the results of applying this method to multiple stock indexes. This analyzes possible to visualize when and where social and economic impacts occur and how they propagate through the earth. This is one of the new applications using this method.
ER -