The Global Machine Readable Filings dataset provides parsed text for corporate annual and interim reports, broken down into the various sections identified by the company, with extraneous information such as page numbers, images, and tables removed.
In this video we introduce Machine Readable Filings (MRF), a universal parser on corporate reports (10-Ks, Global Annual Reports, ESG Reports, etc.) that helps derive trading signals.
Machine Readable Filings
Documents are parsed into Machine Readable data feeds to the item level.
SEC EDGAR, Exclusive Global and ESG Report Libraries.
Proprietary sentiment, word count and topic modeling functionality is applied.
Universal parser can convert any textual file to data feeds.
Never read a full regulatory filing or company report again
Multi-level documents allow user to easily query parts of text they find most relevant.
Users can query on any keywords or synonyms within a specific Part, Item, or sub-section of any document.
Header Level parsing allows for fine grain comparison of document changes over time.
Integrate NLP and Sentiment Metrics into Models
Word Count - Identify net new words, and increases or decreases to total Documents and Sections.
When global firms make an active change in the reporting activities this conveys an important signal about the firm.
With GMRF, clients can break down specific sections and subsequent returns using both Word Count and SMA Sentiment Natural Language Processor.
Use NLP metrics to find changes in company documents YoY or QoQ
Easily find instances when a company adds or removes items from Risk Factors to quickly determine new or non-active risks such as pandemic or trade war risk.
Gain detailed insight into non-US companies and their operations
Expand your company coverage into new international markets with documents covering over 200 countries.
Track changes in international risk factors and management discussion and analysis similar to US regulatory filings.
GMRF takes complicated, international documents (i.e. magazine style) and parses them into reports machine readable multi-level data feeds for seamless integration into alternative data Natural Language Processor models.
Use multi-level data feeds to track changes in a company’s operations, gain insight on new products, and integrate international risk factors into models.
Schedule a Meeting
If you would like to learn more about how our Unstructured Data solutions can benefit you and your team, schedule a call with our CEO, Joe Gits or email us at ContactUs@contextanalytics-ai.com