Praedea DEP Data Lifecycle

• Documents are automatically inserted into the Praedea DEP from virtually any source including SEC filings, FTP sites and internal document management systems and paired with Extraction TemplatesTM for specific document types.
  
  
• Text-mining models for desired terms are built using Praedea’s Term Model Wizard.
  
  
• Data is auto-extracted from documents using the text-mining models.
  
  
• User- and document-specific validation rules are applied (e.g., columns add up, data falls within historical trends, etc.) to assure quality control.
  
  
• Validated data is deposited into a relational database as XML and, if desired, XBRL files.
  
  
• Text-mining models are continually optimized for best performance.
  
  
• Data is delivered into end-user applications with Source Links capability to underlying documents.