A quantitative stock prediction system based on financial news
We examine the problem of discrete stock price prediction using a synthesis of linguistic, financial and statistical techniques to create the Arizona Financial Text System (AZFinText). The research within this paper seeks to contribute to the AZFinText system by comparing AZFinText’s predictions aga...
Gespeichert in:
| Veröffentlicht in: | Information processing & management 2009-09, Vol.45 (5), p.571-583 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 583 |
|---|---|
| container_issue | 5 |
| container_start_page | 571 |
| container_title | Information processing & management |
| container_volume | 45 |
| creator | Schumaker, Robert P. Chen, Hsinchun |
| description | We examine the problem of discrete stock price prediction using a synthesis of linguistic, financial and statistical techniques to create the Arizona Financial Text System (AZFinText).
The research within this paper seeks to contribute to the AZFinText system by comparing AZFinText’s predictions against existing quantitative funds and human stock pricing experts. We approach this line of research using textual representation and statistical machine learning methods on financial news articles partitioned by similar industry and sector groupings. Through our research, we discovered that stocks partitioned by Sectors were most predictable in measures of Closeness, Mean Squared Error (MSE) score of 0.1954, predicted Directional Accuracy of 71.18% and a Simulated Trading return of 8.50% (compared to 5.62% for the S&P 500 index). In direct comparisons to existing market experts and quantitative mutual funds, our system’s trading return of 8.50% outperformed well-known trading experts. Our system also performed well against the top 10 quantitative mutual funds of 2005, where our system would have placed fifth. When comparing AZFinText against only those quantitative funds that monitor the same securities, AZFinText had a 2% higher return than the best performing quant fund. |
| doi_str_mv | 10.1016/j.ipm.2009.05.001 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_57722179</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0306457309000478</els_id><sourcerecordid>1791646111</sourcerecordid><originalsourceid>FETCH-LOGICAL-c385t-d1462f279d5d250e22a5f53225ae86ed8d8bc3feb70afc9b694b5df2c0413aa63</originalsourceid><addsrcrecordid>eNp9kE1LAzEQhoMoWD9-gLdF0Nuuk2SzHwhCKX5BwYueQzaZQOp2tyZppf_elBYPHjwNA8_7zvAQckWhoECru0XhVsuCAbQFiAKAHpEJbWqeC17TYzIBDlVeipqfkrMQFgBQCsom5GGafa3VEF1U0W0wC3HUn9nKo3E6unHIwjZEXGadCmiytFs3qEE71WcDfocLcmJVH_DyMM_Jx9Pj--wln789v86m81zzRsTc0LJiltWtEYYJQMaUsIIzJhQ2FZrGNJ3mFrsalNVtV7VlJ4xlGkrKlar4Obnd9678-LXGEOXSBY19rwYc10GKumaM1m0Cr_-Ai3Hth_SbpG3ZUlGVTYLoHtJ-DMGjlSvvlspvJQW50ykXMumUO50ShEw6U-bmUKyCVr31OwvhN5iON6m_TNz9nsOkY-PQy6AdDjoJ9aijNKP758oPwHGJ5w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>194915648</pqid></control><display><type>article</type><title>A quantitative stock prediction system based on financial news</title><source>Access via ScienceDirect (Elsevier)</source><creator>Schumaker, Robert P. ; Chen, Hsinchun</creator><creatorcontrib>Schumaker, Robert P. ; Chen, Hsinchun</creatorcontrib><description>We examine the problem of discrete stock price prediction using a synthesis of linguistic, financial and statistical techniques to create the Arizona Financial Text System (AZFinText).
The research within this paper seeks to contribute to the AZFinText system by comparing AZFinText’s predictions against existing quantitative funds and human stock pricing experts. We approach this line of research using textual representation and statistical machine learning methods on financial news articles partitioned by similar industry and sector groupings. Through our research, we discovered that stocks partitioned by Sectors were most predictable in measures of Closeness, Mean Squared Error (MSE) score of 0.1954, predicted Directional Accuracy of 71.18% and a Simulated Trading return of 8.50% (compared to 5.62% for the S&P 500 index). In direct comparisons to existing market experts and quantitative mutual funds, our system’s trading return of 8.50% outperformed well-known trading experts. Our system also performed well against the top 10 quantitative mutual funds of 2005, where our system would have placed fifth. When comparing AZFinText against only those quantitative funds that monitor the same securities, AZFinText had a 2% higher return than the best performing quant fund.</description><identifier>ISSN: 0306-4573</identifier><identifier>EISSN: 1873-5371</identifier><identifier>DOI: 10.1016/j.ipm.2009.05.001</identifier><identifier>CODEN: IPMADK</identifier><language>eng</language><publisher>Kidlington: Elsevier Ltd</publisher><subject>Automatic text analysis ; Comparative analysis ; Content analysis ; Exact sciences and technology ; Forecasting techniques ; Information and communication sciences ; Information and document structure and analysis ; Information processing and retrieval ; Information science. Documentation ; Knowledge management ; Mutual funds ; Prediction from textual documents ; Predictions ; Quantitative funds ; Rates of return ; Sciences and techniques of general use ; Scientific and technological watch. Knowledge management ; Stock exchanges ; Stock prices ; Studies</subject><ispartof>Information processing & management, 2009-09, Vol.45 (5), p.571-583</ispartof><rights>2009 Elsevier Ltd</rights><rights>2015 INIST-CNRS</rights><rights>Copyright Pergamon Press Inc. Sep 2009</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c385t-d1462f279d5d250e22a5f53225ae86ed8d8bc3feb70afc9b694b5df2c0413aa63</citedby><cites>FETCH-LOGICAL-c385t-d1462f279d5d250e22a5f53225ae86ed8d8bc3feb70afc9b694b5df2c0413aa63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.ipm.2009.05.001$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=21789494$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Schumaker, Robert P.</creatorcontrib><creatorcontrib>Chen, Hsinchun</creatorcontrib><title>A quantitative stock prediction system based on financial news</title><title>Information processing & management</title><description>We examine the problem of discrete stock price prediction using a synthesis of linguistic, financial and statistical techniques to create the Arizona Financial Text System (AZFinText).
The research within this paper seeks to contribute to the AZFinText system by comparing AZFinText’s predictions against existing quantitative funds and human stock pricing experts. We approach this line of research using textual representation and statistical machine learning methods on financial news articles partitioned by similar industry and sector groupings. Through our research, we discovered that stocks partitioned by Sectors were most predictable in measures of Closeness, Mean Squared Error (MSE) score of 0.1954, predicted Directional Accuracy of 71.18% and a Simulated Trading return of 8.50% (compared to 5.62% for the S&P 500 index). In direct comparisons to existing market experts and quantitative mutual funds, our system’s trading return of 8.50% outperformed well-known trading experts. Our system also performed well against the top 10 quantitative mutual funds of 2005, where our system would have placed fifth. When comparing AZFinText against only those quantitative funds that monitor the same securities, AZFinText had a 2% higher return than the best performing quant fund.</description><subject>Automatic text analysis</subject><subject>Comparative analysis</subject><subject>Content analysis</subject><subject>Exact sciences and technology</subject><subject>Forecasting techniques</subject><subject>Information and communication sciences</subject><subject>Information and document structure and analysis</subject><subject>Information processing and retrieval</subject><subject>Information science. Documentation</subject><subject>Knowledge management</subject><subject>Mutual funds</subject><subject>Prediction from textual documents</subject><subject>Predictions</subject><subject>Quantitative funds</subject><subject>Rates of return</subject><subject>Sciences and techniques of general use</subject><subject>Scientific and technological watch. Knowledge management</subject><subject>Stock exchanges</subject><subject>Stock prices</subject><subject>Studies</subject><issn>0306-4573</issn><issn>1873-5371</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2009</creationdate><recordtype>article</recordtype><recordid>eNp9kE1LAzEQhoMoWD9-gLdF0Nuuk2SzHwhCKX5BwYueQzaZQOp2tyZppf_elBYPHjwNA8_7zvAQckWhoECru0XhVsuCAbQFiAKAHpEJbWqeC17TYzIBDlVeipqfkrMQFgBQCsom5GGafa3VEF1U0W0wC3HUn9nKo3E6unHIwjZEXGadCmiytFs3qEE71WcDfocLcmJVH_DyMM_Jx9Pj--wln789v86m81zzRsTc0LJiltWtEYYJQMaUsIIzJhQ2FZrGNJ3mFrsalNVtV7VlJ4xlGkrKlar4Obnd9678-LXGEOXSBY19rwYc10GKumaM1m0Cr_-Ai3Hth_SbpG3ZUlGVTYLoHtJ-DMGjlSvvlspvJQW50ykXMumUO50ShEw6U-bmUKyCVr31OwvhN5iON6m_TNz9nsOkY-PQy6AdDjoJ9aijNKP758oPwHGJ5w</recordid><startdate>20090901</startdate><enddate>20090901</enddate><creator>Schumaker, Robert P.</creator><creator>Chen, Hsinchun</creator><general>Elsevier Ltd</general><general>Elsevier</general><general>Elsevier Science Ltd</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>E3H</scope><scope>F2A</scope></search><sort><creationdate>20090901</creationdate><title>A quantitative stock prediction system based on financial news</title><author>Schumaker, Robert P. ; Chen, Hsinchun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c385t-d1462f279d5d250e22a5f53225ae86ed8d8bc3feb70afc9b694b5df2c0413aa63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Automatic text analysis</topic><topic>Comparative analysis</topic><topic>Content analysis</topic><topic>Exact sciences and technology</topic><topic>Forecasting techniques</topic><topic>Information and communication sciences</topic><topic>Information and document structure and analysis</topic><topic>Information processing and retrieval</topic><topic>Information science. Documentation</topic><topic>Knowledge management</topic><topic>Mutual funds</topic><topic>Prediction from textual documents</topic><topic>Predictions</topic><topic>Quantitative funds</topic><topic>Rates of return</topic><topic>Sciences and techniques of general use</topic><topic>Scientific and technological watch. Knowledge management</topic><topic>Stock exchanges</topic><topic>Stock prices</topic><topic>Studies</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Schumaker, Robert P.</creatorcontrib><creatorcontrib>Chen, Hsinchun</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Library & Information Sciences Abstracts (LISA)</collection><collection>Library & Information Science Abstracts (LISA)</collection><jtitle>Information processing & management</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Schumaker, Robert P.</au><au>Chen, Hsinchun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A quantitative stock prediction system based on financial news</atitle><jtitle>Information processing & management</jtitle><date>2009-09-01</date><risdate>2009</risdate><volume>45</volume><issue>5</issue><spage>571</spage><epage>583</epage><pages>571-583</pages><issn>0306-4573</issn><eissn>1873-5371</eissn><coden>IPMADK</coden><abstract>We examine the problem of discrete stock price prediction using a synthesis of linguistic, financial and statistical techniques to create the Arizona Financial Text System (AZFinText).
The research within this paper seeks to contribute to the AZFinText system by comparing AZFinText’s predictions against existing quantitative funds and human stock pricing experts. We approach this line of research using textual representation and statistical machine learning methods on financial news articles partitioned by similar industry and sector groupings. Through our research, we discovered that stocks partitioned by Sectors were most predictable in measures of Closeness, Mean Squared Error (MSE) score of 0.1954, predicted Directional Accuracy of 71.18% and a Simulated Trading return of 8.50% (compared to 5.62% for the S&P 500 index). In direct comparisons to existing market experts and quantitative mutual funds, our system’s trading return of 8.50% outperformed well-known trading experts. Our system also performed well against the top 10 quantitative mutual funds of 2005, where our system would have placed fifth. When comparing AZFinText against only those quantitative funds that monitor the same securities, AZFinText had a 2% higher return than the best performing quant fund.</abstract><cop>Kidlington</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.ipm.2009.05.001</doi><tpages>13</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0306-4573 |
| ispartof | Information processing & management, 2009-09, Vol.45 (5), p.571-583 |
| issn | 0306-4573 1873-5371 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_57722179 |
| source | Access via ScienceDirect (Elsevier) |
| subjects | Automatic text analysis Comparative analysis Content analysis Exact sciences and technology Forecasting techniques Information and communication sciences Information and document structure and analysis Information processing and retrieval Information science. Documentation Knowledge management Mutual funds Prediction from textual documents Predictions Quantitative funds Rates of return Sciences and techniques of general use Scientific and technological watch. Knowledge management Stock exchanges Stock prices Studies |
| title | A quantitative stock prediction system based on financial news |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T23%3A38%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20quantitative%20stock%20prediction%20system%20based%20on%20financial%20news&rft.jtitle=Information%20processing%20&%20management&rft.au=Schumaker,%20Robert%20P.&rft.date=2009-09-01&rft.volume=45&rft.issue=5&rft.spage=571&rft.epage=583&rft.pages=571-583&rft.issn=0306-4573&rft.eissn=1873-5371&rft.coden=IPMADK&rft_id=info:doi/10.1016/j.ipm.2009.05.001&rft_dat=%3Cproquest_cross%3E1791646111%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=194915648&rft_id=info:pmid/&rft_els_id=S0306457309000478&rfr_iscdi=true |