Big Data & Text Analytics: As  the analysis  of  large amounts  of unstructured  data is gaining a major space in enterprise  computing,  we  are seeing the emergence of more use cases in this regard.  While  the  term   "Big"  in Big Data   makes it more synonymous  with  Massively Parallel Processing frameworks like Hadoop,  however  the  underlying the success of  Big Data  relies  on effective usage of  content analytics  of the underlying  unstructured data.  I have high lighted  this thought process in my earlier  article, Big Data Analytics Thinking Outside Of Hadoop.

Unstructured Content Analytics is  defined  as the   process of  gaining  new insights  from  the  unstructured data, by  employing   text mining, image recognition, voice recognition and other related analytical techniques.


Big Data Journal was launched on SYS-CON.com in 2012

The below  material  explains   one such use case of  Big Data &  Text Analytics in  getting meaningful insights  from the Financial  Reports.

Financial Reports  & Analytics: All the  publicly  traded  companies in USA & else where  mandatorily  disclose  their corporate information to their  shareholders.  These annual financial statements   are available  as  downloadable reports  on the corporate websites  of  public  companies.   Apart  from the  annual report , there are other forms  of financial statements  like,  investor news letters, Quarterly earning presentation, conference calls by CFO  and other investor relationship documents form part of  an  organization's  financial standing in the eyes  of the  investor.

Most  of the  investors  and  investment analyst  firms  currently  uses  their specialized   knowledge to understand  these financial  statements  and  create meaningful  insights  out of them.  However  these analytics  are mostly limited to the structured  portions  of  the financial statements and not so much  on the unstructured  side of it.

To explain this more :

• For example An annual report may contain statements like Balance Sheet, Income, Equity, Cash Flows etc.. these statements are highly structured and organized as per accounting principles so that any of the qualified financial analysts can understand them
• At the same a typical financial statement also contains lot of unstructured information about growth strategies of the organization, road map, optimism, future vision, how the business model is aligned to the changing times etc...

So   an effective  analysis of  a financial statement  not only pertains  to the structured information but also to the unstructured  data available in the  financial statements.

BigData, UIMA  & Financial Report Analytics: The following   Big Data aligned  technologies  can be effectively used  in analysing the  financial  reports  to derive meaningful insights into the  large volumes  of unstructured data.

• UIMA : UIMA stands for Unstructured Information Management Architecture is the major industry standard for content analytics.

• Annotators : UIMA^TM Annotators do the real work of extracting structured information from unstructured data. You can write your own annotators. Though Annotators form part of UIMA framework lot of custom development is written is creating Annotators specific to the needs of the Finance industry. When documents are processed through the document processing pipeline, the annotators extract concepts, words, phrases, classifications, and named entities from unstructured content and mark these extractions as annotations. The annotations are added to the index as tokens or facets and are used as the source for content analysis.

• Taxonomies : Taxonomies play a major role in identifying the topics of interest within a document using UIMA. In UIMA a type system defines the various types of objects that may be discovered in the document. Types in a UIMA type system may be organized into a taxonomy. For example, Company may be defined as a subtype of Organization

Realizing Financial Statement Analytics & Role of  XBRL: There  are not very many  UIMA  annotators  and  implementation of   text extraction specific to financial statements.  However  we find that,  under  APACHE UIMA community  there is  one such annotator,   The AlchemyAPI Annotator is a set of annotators that wrap the AlchemyAPI.

AlchemyAPI's  (http://www.alchemyapi.com/api/)  Categorization service can be used to categorize text, HTML, or web-based content, assigning the most likely topic category (news, sports, business, etc.).  The business categories  include  topics like, Business and Finance News, SEC filings, etc.

There  are  several  of  the   text analytics concepts  like  the below,  can be applied on the financial statements

• Named Entity Extraction : Identify people, companies, organizations, cities, geographic features, and other typed entities within HTML pages and text documents/content.
• Concept Tagging : Automatically tag documents and text in a manner similar to human-based tagging.
• Keyword / Term Extraction : Extract important terms and "topic" keywords from HTML pages and text documents/content. Advanced statistical and linguistic algorithms analyze your content, "tagging" it with the most important words and phrases.
• Sentiment Analysis : Identify positive, negative and neutral sentiment within HTML pages and text documents/content.
• Relation Extraction : Identify facts and Subject-Action-Object relations within HTML pages and text documents/content.

Apart  from  the  already  developed  and community  supported  annotators,  we could   develop  new annotators  which  can take the best use of already  established  taxonomies  for the financial industry   in the form of  XBRL.

XBRL stands for eXtensible Business Reporting Language. It is a language for the electronic communication of business information, providing major benefits in the preparation, analysis and communication of business information. It is one of a family of "XML" languages which is a standard means of communicating information between businesses and on the internet.

XBRL Taxonomies,  are the dictionaries which the language uses. These are the categorization schemes which define the specific tags for individual items of data (such as "net profit").  National jurisdictions have different accounting regulations, so each may have its own.  There are already well established  approved taxonomies  for  financial reporting  like  XBRL  US  GAAP  as listed in the  site, http://www.xbrl.org/FRTApproved.

As  evident  from  the  architecture  of UIMA  and annotator  entity extraction process, these established  taxonomies  can play a major role in areas like concept tagging,  which  can help in  getting the  meaningful insights  from    large  amounts of  textual and other  unstructured content in the financial statements.

Summary: As  enterprises  and analytics vendors  adopt  Big Data  as part of the mainstream ,  this  adoption will be  more meaningful  to  enable   the technology  to support new  business use cases.  Financial  Analytics  is  one such important area  ,  and with the support of    frameworks like UIMA  coupled  with  industry established taxonomies,  such  analytics  are quite possible  and worth to be implemented.

• TerraEchos Named First North American Reseller of InfoSphere Streams for Big Data-in-Motion Analytics
• Public Sector Big Data: Five Ways Big Data Must Evolve in 2013
• Big Data May Have Big Problems in 2013