Jump to content

PolyAnalyst

Edit links
From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by Sam at Megaputer (talk | contribs) at 04:03, 31 January 2021 (→‎Academic: ce). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

  • Comment: Note to reviewer: Please read these comments from bottom to top to view them in chronological order. Sam at Megaputer (talk) 16:07, 19 October 2020 (UTC)
  • Comment: Note to reviewer: Per Template:COI: "if you place this tag, you should promptly start a discussion on the article's talk page to explain what is non-neutral about the article. If you do not start a discussion, any editor will be justified in removing the tag without warning." Cassiopeia placed that tag, but showed no interest in starting such discussion, despite being asked to several times. I was justified in removing the tag. @Cassiopeia: Please stop spamming up the feed with these baseless WP:aspersions. If you have anything to add to this discussion, please do it on the talk page. Sam at Megaputer (talk) 12:35, 10 October 2020 (UTC)
  • Comment: Reviewer NOTE: Creator whos has a direct COI where he works for the company where its product is PolyAnalyst has removed the COI tag. Cassiopeia(talk) 00:44, 10 October 2020 (UTC)
  • Comment: Confirmed, when the AFC reviewer uses the AFC review tool to add a comment, it sorts the comments newest-to-oldest. davidwr/(talk)/(contribs) 02:45, 8 October 2020 (UTC)
  • Comment: This is a test comment to see what order the AFC review tool puts the comments in when it adds a new comment. davidwr/(talk)/(contribs) 02:44, 8 October 2020 (UTC)
  • Comment: NOTE TO Reviewers - If the COI is removed by anyone pls note that creator works for Megaputer Intelligence who created a page for the company's PolyAnalyst software which means creator has a direct COI here - see User:Sam at Megaputer and creator has been blocked (message removed by creator - see his diff here.. Cassiopeia(talk) 01:03, 8 October 2020 (UTC)
  • Comment: Reviewers- pls note creator has changed they comments - see hist diff here. Cassiopeia(talk) 01:00, 8 October 2020 (UTC)
  • Comment: As that last diff shows, my COI was already disclosed on my user page this whole time. I do not like the implication that it wasn't. Please do not use this thread to cast further WP:ASPERSIONS. Please do not reverse the order of these comments, as you have done twice. It is not necessary to reply further. Sam at Megaputer (talk) 13:25, 7 October 2020 (UTC)
  • Comment: Creator has added the COI article disclose template on their user page - see here. Thank you. Cassiopeia(talk) 07:08, 7 October 2020 (UTC)
  • Comment: I'm sure they already did. As discussed on the talk page, I am not an have never been in violation of COI guidelines. Sam at Megaputer (talk) 00:05, 7 October 2020 (UTC)
  • Comment: NOTE TO REVIEWER: Pls read "COI disclosure" and "Connected contributor template" at the talk page prior reviewing the page. Cassiopeia(talk) 22:11, 6 October 2020 (UTC)
  • Comment: As discussed on the talk page, my COI declaration in text was probably OK already, but I have added a userbox to my page anyway. I am being very open about my COI. Sam at Megaputer (talk) 18:43, 6 October 2020 (UTC)
  • Comment: I suggest you to read the link again on how to disclose user page COI on article you created with COI. Cassiopeia(talk) 02:57, 6 October 2020 (UTC)
  • Comment: Please note again that I have already declared my COI on my user page. At no time did I fail to properly declare my COI! Sam at Megaputer (talk) 02:53, 6 October 2020 (UTC)
  • Comment: As of this edit, creator has yet to disclose their COI - pls see WP:DISCLOSE for article talk page instructions. Cassiopeia(talk) 02:49, 6 October 2020 (UTC)
  • Comment: I would like it noted that my COI was already declared on my user page at the time the above below comment was posted, and has been declared there since before my very first edit to this article. I don't want anyone to think that I have failed to properly disclose my COI. Sam at Megaputer (talk) 02:05, 6 October 2020 (UTC)
  • Comment: Pls note that you need to disclose your COI (you work for Megaputer Intelligence where you create a page for the company's PolyAnalyst software) not only in the article talk page (which you have declared) but also on your user page. Cassiopeia(talk) 00:49, 6 October 2020 (UTC)
PolyAnalyst
Developer(s)Megaputer Intelligence
Stable release
6.5
TypeData science, machine learning, predictive analytics

Polyanalyst is a data science software platform developed by Megaputer Intelligence that provides an environment for text mining, data mining, machine learning, and predictive analytics. It is used by Megaputer to build tools with applications to health care, business management, insurance, and other industries. PolyAnalyst has also been used for COVID-19 forecasting.

Overview

A screenshot of a PolyAnalyst flowchart showing the use of a convolutional neural network node.

PolyAnalyst's graphical user interface contains various nodes that can be linked into a flowchart to perform an analysis. The software provides nodes for data import, data preparation, data visualization, data analysis, and data export.[1][2] After an analysis is complete, the result may be published to a web report.[3]

PolyAnalyst supports text analytics through nodes that rely on machine learning algorithms and a proprietary programming language called PDL (Pattern Definition Language).[4] PolyAnalyst's text analytics features include nodes for text clustering, sentiment analysis, extraction of facts, keywords, and entities, and the creation of taxonomies and ontologies. Polyanalyst also contains nodes for the analysis of structured data and to execute code in Python and R.[5][6] As of 2020, the software supports text analysis in 16 languages.[7]

PolyAnalyst is typically used by Megaputer to build custom tools for businesses. It uses a client–server model and is licensed under a software as a service model.[3]

Applications

Insurance

PolyAnalyst was used to build a subrogation prediction tool which can assist in identifying subrogatable insurance claims. The tool determines the probability that a claim is subrogatable, and if so, the amount that is expected to be recovered. It is used by insurance companies to reduce the need for manual review of insurance claims and to increase the accuracy of subrogation predictions.[8] PolyAnalyst is also used to detect insurance fraud.[9]

Business Management

Two case studies have found that PolyAnalyst can be used to improve hotel management and customer service.[10][11] PolyAnalyst is also used to analyze product review data, warranty claims, customer comments, and other written customer feedback.[12] In one case, PolyAnalyst was used to build a tool to help a company evaluate its associates conversations with customers by rating their messages for factors such as professionalism, empathy, and correctness of response. The company reported to Forrester Research that the tool saved them around $11.8 million annually.[13]

Health care

PolyAnalyst is used by pharmaceutical companies to assist in pharmacovigilance. The software was used to design a tool that matches descriptions of adverse events to their proper MedDRA codes, determines if side-effects are serious or non-serious, and to set up cases for ongoing monitoring if needed.[14] PolyAnalyst has also been applied to discover new uses for existing drugs by text mining ClinicalTrials.gov[15] and to forecast the spread of the COVID-19 virus in the United States and Russia.[16][17]

Academic

PolyAnalyst is run on the SKIF Cyberia Supercomputer at Tomsk State University where researchers have used it to manage university endowment funds, to assess the university's social media image, and to create educational modules for the school of applied data analysis.[18] Polyanalyst has also been used by researchers at Vyatka State University to locate victims of spousal abuse through social media analysis.[19]

References

  1. ^ Apicella, Mario (July 3, 2000). "PolyAnalyst 4.1 digs through data for gold". Info World.{{cite news}}: CS1 maint: url-status (link)
  2. ^ Zhang, Qingyu; Segall, Richard S. (2008-12-01). "Web mining: a survey of current research, techniques, and software". International Journal of Information Technology & Decision Making. 07 (4): 683–720. doi:10.1142/S0219622008003150. ISSN 0219-6220.
  3. ^ a b Halper, Fern (2011). "Predictive Analytics: The Hurwitz Victory Index Report" (PDF). Retrieved 28 September 2020.{{cite web}}: CS1 maint: url-status (link)
  4. ^ Bourlai, Elli (2020-02-12). "Combining the Best of Both Worlds: Machine Learning & Rule-Based Approach". Megaputer Intelligence. Retrieved 2020-10-03.
  5. ^ Zhang, Qingyu; Segall, Richard S. (2010-01-01). "Review of data, text and web mining software". Kybernetes. 39 (4): 625–655. doi:10.1108/03684921011036835. ISSN 0368-492X.
  6. ^ Zhang, Qingyu; Segall, Richard S. (2010), Maimon, Oded; Rokach, Lior (eds.), "Commercial Data Mining Software", Data Mining and Knowledge Discovery Handbook, Boston, MA: Springer US, pp. 1245–1268, Bibcode:2010dmak.book.1245Z, doi:10.1007/978-0-387-09823-4_65, ISBN 978-0-387-09823-4, retrieved 2020-10-03
  7. ^ "PolyAnalyst for Text Software". Megaputer Intelligence. Retrieved 2020-09-28.
  8. ^ "Megaputer Intelligence". big-data.insuranceciooutlook.com. Retrieved 2020-09-21.
  9. ^ Wang, John; Yang, James G. S. "Data Mining Techniques for Auditing Attest Function and Fraud Detection". CiteSeerX 10.1.1.453.5506. Retrieved 21 September 2020. {{cite journal}}: Cite journal requires |journal= (help)
  10. ^ Sharma, Arvind K. "Web Mining Techniques to Improve Hotel Management Services". CiteSeerX 10.1.1.415.9763. Retrieved 22 September 2020. {{cite journal}}: Cite journal requires |journal= (help)
  11. ^ "Web Mining of Hotel Customer Survey Data". Citeseerx.ist.psu.edu. CiteSeerX 10.1.1.455.7659. Retrieved 27 September 2020.
  12. ^ "Market Guide for Text Analytics". 31 August 2020.{{cite web}}: CS1 maint: url-status (link)
  13. ^ Evelson, Boris (November 10, 2015). "Vendor Landscape: Big Data Text Analytics". Forrester.{{cite news}}: CS1 maint: url-status (link)
  14. ^ "Life sciences: Increasing speed-to-insight in pharma". www.kmworld.com. Retrieved 2020-09-22.
  15. ^ Su, Eric Wen; Sanger, Todd M. (2017-03-23). "Systematic drug repositioning through mining adverse event data in ClinicalTrials.gov". PeerJ. 5: e3154. doi:10.7717/peerj.3154. ISSN 2167-8359. PMC 5366063. PMID 28348935.{{cite journal}}: CS1 maint: unflagged free DOI (link)
  16. ^ Codingest (2020-04-29). "COVID-19: Megaputer provides interactive geo-map to forecast peak of active cases in U.S." thegeospatial. Retrieved 2020-09-30.
  17. ^ "В России представили модели пика заболеваемости COVID-19 в регионах". РБК (in Russian). Retrieved 2020-09-24.
  18. ^ редакция, Любимая. "В ТГУ открылся Центр коллективного пользования платформой для аналитики big data". Томский Обзор (in Russian). Retrieved 25 January 2021.
  19. ^ Адрес: 119234, Учредитель: Некоммерческое партнерство «Международное партнерство распространения научных знаний»; Москва, г; горы, Ленинские; адрес: 119234, офис 138 Почтовый; Москва, г; Университетская, пл; Тел./Факс: +7939-42-66, а/я №71; до 18-00, +7939-45-63 Время работы: с 10-00 (24 January 2021). "Искусственный интеллект выяснил, куда чаще обращаются за помощью жертвы семейного насилия в России". «Научная Россия» — наука в деталях! (in Russian). Retrieved 25 January 2021.{{cite web}}: CS1 maint: numeric names: authors list (link)

Official website

Retrieved from "https://en.wikipedia.org/w/index.php?title=PolyAnalyst&oldid=1003881105"