Poly Analyst text mining tool Allstate Insurance example

Poly. Analyst™ text mining tool Allstate Insurance example Sergei Ananyan Megaputer Intelligence (812) 330 -0110 sananyan@megaputer. com © 2008 Megaputer Intelligence

Poly. Analyst Overview © 2008 Megaputer Intelligence

Poly. Analyst™ text mining tool • Knowledge discovery tool for business users • Easy-to-understand actionable results Data Overload Useful Knowledge Poly. Analyst © 2008 Megaputer Intelligence TM

Text Mining with Poly. Analyst Data Analyst Collecting & Storing Data Automated Text Analysis Generating Reports Decision Maker © 2008 Megaputer Intelligence

Capabilities of Poly. Analyst • Unlocks value hidden in massive volumes of data and text • Solves many typical text analysis tasks: – – – – Categorization Clustering Taxonomy building Entity extraction Natural language search Multi-dimensional reporting Visual link analysis • Enterprise level scalability • Visual creation of analysis scenarios • Interactive visualization and drill-down • Executive reports © 2008 Megaputer Intelligence

Poly. Analyst extra features • In addition, Poly. Analyst offers the following features: – – – Automated spelling correction Negation detection Sentiment analysis Words and patterns search Ability to discover unexpected issues Dictionary editor for synonyms, abbreviations and stop-words © 2008 Megaputer Intelligence

Handled Business Tasks • Survey data analysis • Call Center data analysis • Repair notes analysis • Incident report analysis • Claims notes analysis • E-mail target routing • Competitive intelligence • Fraud detection • Intellectual property research © 2008 Megaputer Intelligence

Poly. Analyst application domains Government Insurance Financial High Tech Consumer Products Manufacturing © 2008 Megaputer Intelligence

Step 1. Data Analysis © 2008 Megaputer Intelligence

Poly. Analyst Data Analysis Scenarios © 2008 Megaputer Intelligence

Data Loading and Integration • Import the data for analysis: any database, document collection, Internet, RSS, and mail server • Merge data from different sources • Unify and prepare records for analysis © 2008 Megaputer Intelligence

Keyword Extraction • Extracts keywords that comprise the investigated documents • Displays all records for a selected keyword with the word highlighted © 2008 Megaputer Intelligence

Phrase Extraction • Extracts phrases and stable combinations of words © 2008 Megaputer Intelligence

Visualization of Clusters and Patterns • Provides drill-down capability to review specific cases © 2008 Megaputer Intelligence

Entity Extraction • Extracts company names, geographic locations, date stamps, currency amounts, telephones, URLs, e-mails, etc. © 2008 Megaputer Intelligence

Document Clustering • Hierarchical or binary grouping of documents • Automated creation of a tentative taxonomy for categorization © 2008 Megaputer Intelligence

Document Categorization • Review the clustering results to introduce custom changes in the categorization patterns © 2008 Megaputer Intelligence

Visualizing Categorization Results • Charts support dynamic drill-downs to original documents © 2008 Megaputer Intelligence

Advanced Search Engine • Offers term proximity searches, dictionary-based searches and more © 2008 Megaputer Intelligence

Dictionary Management • Dictionaries provide the base for linguistic-based search and categorization functions, maintain lists of known and stop words • Dictionary Manager allows to importing or creating domain-specific thesauri © 2008 Megaputer Intelligence

Step 2. Reporting Poly. Analyst for Business Users © 2008 Megaputer Intelligence

Site Manager’s Report: Food & Beverage © 2008 Megaputer Intelligence

Site Manager’s Report: Villa Cleanliness © 2008 Megaputer Intelligence

Benefits of Text Mining with Poly. Analyst © 2008 Megaputer Intelligence

Benefits • Extracting value from massive volumes of text • Dramatic reduction in the cost of data analysis • Increase in quality and speed of the analysis – Poly. Analyst successfully categorizes 95% of text records – Poly. Analyst provides 10, 000 time better speed than manual analysis • Automated monitoring of data for known problems • Timely discovery of emerging issues and trends • Joint analysis of text and structured data • Objective and uniform data-driven analysis • Delivering interactive report to decision makers © 2008 Megaputer Intelligence

Next Steps Call (812) 330 -0110 or write sananyan@megaputer. com 120 W Seventh Street, Suite 314 Bloomington, IN 47404 USA © 2008 Megaputer Intelligence