Are you trying to work with SEC Filings?
Do you already know what you want?
What content exists?
Where to find it? Which Filings, Attachments, Sections?
How to gather it?
The right set of queries?
All the valid synonyms and phrases?
How to avoid drowning in false positives?
10-K, 10-Q, 8-K, Proxy Statements, Annual Reports
Comment Letters, Material Definitive Agreements
Plans of Acquisition, Reorganization or Liquidation
etc …
Are you looking for better ways to explore SEC Filings
Maybe you would prefer …
Interactive Map - an interactive map that provides a visual summary
of the content, allowing zoom in and out of the content?
Hierarchical Headings - to explore headings instead of just keywords?
Themes or Topics - to use themes or topics to take slices of content?
Context - to perform contextual searches instead of just word
proximity? To easily navigate to what is surrounding content of
interest. To see suggestions of similar searches and similar content?
Semantics - to explore semantics, to find unexpected synonyms,
compound terms or disambiguate concepts? To be able to interact with
term semantics quantitatively?
Deviants - to know which content is standard and which is deviant and
how it diverges?
Terminology - to see what terminology exists before you finish
entering a query?
Are you looking to perform Data Science on SEC Filings
Looking for …
Better Ingredients
Cleanly parsed sections or subsections or footnotes of specific
Easily filtered - to remove superfluous content such as boiler plate
content, table of contents, document colophon, page headers,
page numbers, etc
Better Tools
Visually oriented - navigation and filtering treating queries and
results as compositional units, viewable in multiple ways
Machine Learning algorithms- you can apply on the fly against
specific sub sections of specific filings?
A query driven approach - to feed your machine learning
algorithms cleanly parsed fragments rather having to build a
custom data munging on your own?
Are you a Data Scientist looking for
clean normalized data?
Just looking for flexibility and performance …
An API - well organized and flexible
Streaming - specific sub sections of specific
filings to you at a high rate …
Are you sure you are avoiding Author Bias?
Key word search - If you are relying on key word
search to find your content of interest … how do you
know you have identified all the relevant keywords,
the correct synonyms and phrases?
Statistically Quantifiable - Would you prefer an
objective statistically quantifiable means of
assessing that you are looking at the right content?
Research accomplished using the
SEC Filing Analyzer?
Do you have a research project?
An interesting insight that you just can not find the
tools for?
An interest in content not previously analyzed?
Just looking for flexibility and performance …