Detection of Stock Price Manipulation Using Kernel Based Principal Component Analysis and Multivariate Density Estimation

Stock price manipulation uses illegitimate means to artificially influence market prices of several stocks. It causes massive losses and undermines investors' confidence and the integrity of the stock market. Several existing research works focused on detecting a specific manipulation scheme us...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE access 2020, Vol.8, p.135989-136003
Hauptverfasser: Rizvi, Baqar, Belatreche, Ammar, Bouridane, Ahmed, Watson, Ian
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 136003
container_issue
container_start_page 135989
container_title IEEE access
container_volume 8
creator Rizvi, Baqar
Belatreche, Ammar
Bouridane, Ahmed
Watson, Ian
description Stock price manipulation uses illegitimate means to artificially influence market prices of several stocks. It causes massive losses and undermines investors' confidence and the integrity of the stock market. Several existing research works focused on detecting a specific manipulation scheme using supervised learning but lacks the adaptive capability to capture different manipulative strategies. This begets the assumption of model parameter values specific to the underlying manipulation scheme. In addition, supervised learning requires the use of labelled data which is difficult to acquire due to confidentiality and the proprietary nature of trading data. The proposed research establishes a detection model based on unsupervised learning using Kernel Principal Component Analysis (KPCA) and applied increased variance of selected latent features in higher dimensions. A proposed Multidimensional Kernel Density Estimation (MKDE) clustering is then applied upon the selected components to identify abnormal patterns of manipulation in data. This research has an advantage over the existing methods in overcoming the ambiguity of assuming values of several parameters, reducing the high dimensions obtained from conventional KPCA and thereby reducing computational complexity. The robustness of the detection model has also been evaluated when two or more manipulative activities occur within a short duration of each other and by varying the window length of the dataset fed to the model. Validation on multiple datasets and a comprehensive assessment of the model performance has been conducted without providing any prior information about the location of the manipulation. The results show a significant performance enhancement in terms of the F-measure values and a significant reduction in false alarm rate (FAR) has been achieved.
doi_str_mv 10.1109/ACCESS.2020.3011590
format Article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_proquest_journals_2454642471</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9146609</ieee_id><doaj_id>oai_doaj_org_article_8ae7262036624f8fa6e9426c006334f7</doaj_id><sourcerecordid>2454642471</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-6a5482b32e791ba9703d50b0881a171549a2d0db69b930d8e33e48fd5db3348a3</originalsourceid><addsrcrecordid>eNpNkU9r3DAQxU1poSHNJ8hF0PNu9c-ydNw62zY0IYVtzmJsjYO2juRK2sJ--3rXIUSXETPv_YbhVdU1o2vGqPmyadvtbrfmlNO1oIzVhr6rLjhTZiVqod6_-X-srnLe0_npuVU3F9XxBgv2xcdA4kB2JfZ_yK_keyT3EPx0GOE8e8w-PJGfmAKO5CtkdCdV6P0EI2nj8xQDhkI2AcZj9plAcOT-MBb_D5KHguQGQ_blSLa5-Ocz81P1YYAx49VLvawev21_tz9Wdw_fb9vN3aqXVJeVglpq3gmOjWEdmIYKV9OOas2ANayWBrijrlOmM4I6jUKg1IOrXSeE1CAuq9uF6yLs7ZTm9eloI3h7bsT0ZCEV349oNWDDFadCKS4HPYBCI7nqKVUza2hm1ueFNaX494C52H08pPnobLmspZJcNmxWiUXVp5hzwuF1K6P2FJldIrOnyOxLZLPrenF5RHx1GCaVokb8B54Rkdw</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2454642471</pqid></control><display><type>article</type><title>Detection of Stock Price Manipulation Using Kernel Based Principal Component Analysis and Multivariate Density Estimation</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Rizvi, Baqar ; Belatreche, Ammar ; Bouridane, Ahmed ; Watson, Ian</creator><creatorcontrib>Rizvi, Baqar ; Belatreche, Ammar ; Bouridane, Ahmed ; Watson, Ian</creatorcontrib><description>Stock price manipulation uses illegitimate means to artificially influence market prices of several stocks. It causes massive losses and undermines investors' confidence and the integrity of the stock market. Several existing research works focused on detecting a specific manipulation scheme using supervised learning but lacks the adaptive capability to capture different manipulative strategies. This begets the assumption of model parameter values specific to the underlying manipulation scheme. In addition, supervised learning requires the use of labelled data which is difficult to acquire due to confidentiality and the proprietary nature of trading data. The proposed research establishes a detection model based on unsupervised learning using Kernel Principal Component Analysis (KPCA) and applied increased variance of selected latent features in higher dimensions. A proposed Multidimensional Kernel Density Estimation (MKDE) clustering is then applied upon the selected components to identify abnormal patterns of manipulation in data. This research has an advantage over the existing methods in overcoming the ambiguity of assuming values of several parameters, reducing the high dimensions obtained from conventional KPCA and thereby reducing computational complexity. The robustness of the detection model has also been evaluated when two or more manipulative activities occur within a short duration of each other and by varying the window length of the dataset fed to the model. Validation on multiple datasets and a comprehensive assessment of the model performance has been conducted without providing any prior information about the location of the manipulation. The results show a significant performance enhancement in terms of the F-measure values and a significant reduction in false alarm rate (FAR) has been achieved.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2020.3011590</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>anomaly detection ; Clustering ; Computational modeling ; Confidence ; Data models ; Datasets ; Density ; False alarms ; Feature extraction ; Kernel ; kernel principal component analyses ; Kernels ; Manipulators ; Market abuse ; Mathematical models ; multi-dimensional kernel density estimate clustering ; Parameters ; Performance enhancement ; Pricing ; Principal component analysis ; Principal components analysis ; Robustness (mathematics) ; Stock markets ; stock price manipulation ; Supervised learning</subject><ispartof>IEEE access, 2020, Vol.8, p.135989-136003</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-6a5482b32e791ba9703d50b0881a171549a2d0db69b930d8e33e48fd5db3348a3</citedby><cites>FETCH-LOGICAL-c408t-6a5482b32e791ba9703d50b0881a171549a2d0db69b930d8e33e48fd5db3348a3</cites><orcidid>0000-0002-1474-2772 ; 0000-0002-6913-976X ; 0000-0003-1927-9366</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9146609$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,860,2096,4010,27610,27900,27901,27902,54908</link.rule.ids></links><search><creatorcontrib>Rizvi, Baqar</creatorcontrib><creatorcontrib>Belatreche, Ammar</creatorcontrib><creatorcontrib>Bouridane, Ahmed</creatorcontrib><creatorcontrib>Watson, Ian</creatorcontrib><title>Detection of Stock Price Manipulation Using Kernel Based Principal Component Analysis and Multivariate Density Estimation</title><title>IEEE access</title><addtitle>Access</addtitle><description>Stock price manipulation uses illegitimate means to artificially influence market prices of several stocks. It causes massive losses and undermines investors' confidence and the integrity of the stock market. Several existing research works focused on detecting a specific manipulation scheme using supervised learning but lacks the adaptive capability to capture different manipulative strategies. This begets the assumption of model parameter values specific to the underlying manipulation scheme. In addition, supervised learning requires the use of labelled data which is difficult to acquire due to confidentiality and the proprietary nature of trading data. The proposed research establishes a detection model based on unsupervised learning using Kernel Principal Component Analysis (KPCA) and applied increased variance of selected latent features in higher dimensions. A proposed Multidimensional Kernel Density Estimation (MKDE) clustering is then applied upon the selected components to identify abnormal patterns of manipulation in data. This research has an advantage over the existing methods in overcoming the ambiguity of assuming values of several parameters, reducing the high dimensions obtained from conventional KPCA and thereby reducing computational complexity. The robustness of the detection model has also been evaluated when two or more manipulative activities occur within a short duration of each other and by varying the window length of the dataset fed to the model. Validation on multiple datasets and a comprehensive assessment of the model performance has been conducted without providing any prior information about the location of the manipulation. The results show a significant performance enhancement in terms of the F-measure values and a significant reduction in false alarm rate (FAR) has been achieved.</description><subject>anomaly detection</subject><subject>Clustering</subject><subject>Computational modeling</subject><subject>Confidence</subject><subject>Data models</subject><subject>Datasets</subject><subject>Density</subject><subject>False alarms</subject><subject>Feature extraction</subject><subject>Kernel</subject><subject>kernel principal component analyses</subject><subject>Kernels</subject><subject>Manipulators</subject><subject>Market abuse</subject><subject>Mathematical models</subject><subject>multi-dimensional kernel density estimate clustering</subject><subject>Parameters</subject><subject>Performance enhancement</subject><subject>Pricing</subject><subject>Principal component analysis</subject><subject>Principal components analysis</subject><subject>Robustness (mathematics)</subject><subject>Stock markets</subject><subject>stock price manipulation</subject><subject>Supervised learning</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNkU9r3DAQxU1poSHNJ8hF0PNu9c-ydNw62zY0IYVtzmJsjYO2juRK2sJ--3rXIUSXETPv_YbhVdU1o2vGqPmyadvtbrfmlNO1oIzVhr6rLjhTZiVqod6_-X-srnLe0_npuVU3F9XxBgv2xcdA4kB2JfZ_yK_keyT3EPx0GOE8e8w-PJGfmAKO5CtkdCdV6P0EI2nj8xQDhkI2AcZj9plAcOT-MBb_D5KHguQGQ_blSLa5-Ocz81P1YYAx49VLvawev21_tz9Wdw_fb9vN3aqXVJeVglpq3gmOjWEdmIYKV9OOas2ANayWBrijrlOmM4I6jUKg1IOrXSeE1CAuq9uF6yLs7ZTm9eloI3h7bsT0ZCEV349oNWDDFadCKS4HPYBCI7nqKVUza2hm1ueFNaX494C52H08pPnobLmspZJcNmxWiUXVp5hzwuF1K6P2FJldIrOnyOxLZLPrenF5RHx1GCaVokb8B54Rkdw</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>Rizvi, Baqar</creator><creator>Belatreche, Ammar</creator><creator>Bouridane, Ahmed</creator><creator>Watson, Ian</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-1474-2772</orcidid><orcidid>https://orcid.org/0000-0002-6913-976X</orcidid><orcidid>https://orcid.org/0000-0003-1927-9366</orcidid></search><sort><creationdate>2020</creationdate><title>Detection of Stock Price Manipulation Using Kernel Based Principal Component Analysis and Multivariate Density Estimation</title><author>Rizvi, Baqar ; Belatreche, Ammar ; Bouridane, Ahmed ; Watson, Ian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-6a5482b32e791ba9703d50b0881a171549a2d0db69b930d8e33e48fd5db3348a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>anomaly detection</topic><topic>Clustering</topic><topic>Computational modeling</topic><topic>Confidence</topic><topic>Data models</topic><topic>Datasets</topic><topic>Density</topic><topic>False alarms</topic><topic>Feature extraction</topic><topic>Kernel</topic><topic>kernel principal component analyses</topic><topic>Kernels</topic><topic>Manipulators</topic><topic>Market abuse</topic><topic>Mathematical models</topic><topic>multi-dimensional kernel density estimate clustering</topic><topic>Parameters</topic><topic>Performance enhancement</topic><topic>Pricing</topic><topic>Principal component analysis</topic><topic>Principal components analysis</topic><topic>Robustness (mathematics)</topic><topic>Stock markets</topic><topic>stock price manipulation</topic><topic>Supervised learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Rizvi, Baqar</creatorcontrib><creatorcontrib>Belatreche, Ammar</creatorcontrib><creatorcontrib>Bouridane, Ahmed</creatorcontrib><creatorcontrib>Watson, Ian</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rizvi, Baqar</au><au>Belatreche, Ammar</au><au>Bouridane, Ahmed</au><au>Watson, Ian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Detection of Stock Price Manipulation Using Kernel Based Principal Component Analysis and Multivariate Density Estimation</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2020</date><risdate>2020</risdate><volume>8</volume><spage>135989</spage><epage>136003</epage><pages>135989-136003</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Stock price manipulation uses illegitimate means to artificially influence market prices of several stocks. It causes massive losses and undermines investors' confidence and the integrity of the stock market. Several existing research works focused on detecting a specific manipulation scheme using supervised learning but lacks the adaptive capability to capture different manipulative strategies. This begets the assumption of model parameter values specific to the underlying manipulation scheme. In addition, supervised learning requires the use of labelled data which is difficult to acquire due to confidentiality and the proprietary nature of trading data. The proposed research establishes a detection model based on unsupervised learning using Kernel Principal Component Analysis (KPCA) and applied increased variance of selected latent features in higher dimensions. A proposed Multidimensional Kernel Density Estimation (MKDE) clustering is then applied upon the selected components to identify abnormal patterns of manipulation in data. This research has an advantage over the existing methods in overcoming the ambiguity of assuming values of several parameters, reducing the high dimensions obtained from conventional KPCA and thereby reducing computational complexity. The robustness of the detection model has also been evaluated when two or more manipulative activities occur within a short duration of each other and by varying the window length of the dataset fed to the model. Validation on multiple datasets and a comprehensive assessment of the model performance has been conducted without providing any prior information about the location of the manipulation. The results show a significant performance enhancement in terms of the F-measure values and a significant reduction in false alarm rate (FAR) has been achieved.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2020.3011590</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0002-1474-2772</orcidid><orcidid>https://orcid.org/0000-0002-6913-976X</orcidid><orcidid>https://orcid.org/0000-0003-1927-9366</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2169-3536
ispartof IEEE access, 2020, Vol.8, p.135989-136003
issn 2169-3536
2169-3536
language eng
recordid cdi_proquest_journals_2454642471
source IEEE Open Access Journals; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals
subjects anomaly detection
Clustering
Computational modeling
Confidence
Data models
Datasets
Density
False alarms
Feature extraction
Kernel
kernel principal component analyses
Kernels
Manipulators
Market abuse
Mathematical models
multi-dimensional kernel density estimate clustering
Parameters
Performance enhancement
Pricing
Principal component analysis
Principal components analysis
Robustness (mathematics)
Stock markets
stock price manipulation
Supervised learning
title Detection of Stock Price Manipulation Using Kernel Based Principal Component Analysis and Multivariate Density Estimation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T00%3A58%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Detection%20of%20Stock%20Price%20Manipulation%20Using%20Kernel%20Based%20Principal%20Component%20Analysis%20and%20Multivariate%20Density%20Estimation&rft.jtitle=IEEE%20access&rft.au=Rizvi,%20Baqar&rft.date=2020&rft.volume=8&rft.spage=135989&rft.epage=136003&rft.pages=135989-136003&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2020.3011590&rft_dat=%3Cproquest_doaj_%3E2454642471%3C/proquest_doaj_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2454642471&rft_id=info:pmid/&rft_ieee_id=9146609&rft_doaj_id=oai_doaj_org_article_8ae7262036624f8fa6e9426c006334f7&rfr_iscdi=true