Data Simply collects, scrubs, verifies, and continually updates data from published company disclosures with the SEC. They derive ESG (environmental, social, and governance) and financial signal data from the words in these documents using custom ontologies to create a consolidated and comprehensive dataset.
Data Simply collects, scrubs, verifies, and continually updates data from published company disclosures with the SEC. It derives ESG (environmental, social, and governance) and financial signal data from the words in these documents using custom ontologies to create a consolidated and comprehensive dataset.
The product information and content statistics contained in this document are as of August 2019.
The Data Simply DataFeed provides data back to 2016 on a monthly frequency. The coverage universe mirrors that of the Russell 3000.
The below tables provide a breakdown of the Data Simply universe by RBICS Sector.
Data Simply leverages a proprietary Financial Intelligence Engine, developed by a team with deep financial services and engineering expertise, to analyze large volumes of text in company SEC filings disclosures. The engine is run on the SEC Edgar database to turn company filings into investment signals that can be leveraged by investment professionals. These signals indicate ESG disclosures as well as financial sentiment, which can indicate the financial health of a company.
A key to the semantic engine is its ability to interpret information like a financial analyst, identifying trends, patterns, and flags. By generating scores through this approach, Data Simply ensures there is no human bias inserted into the data.
Example Use Case
Data Simply uses AI to mine and tag text in the Edgar SEC filings for more than 200 curated concepts. Stemming is employed, which broadens the concept universe to find related words. This analysis creates an output of scores on both ESG and financial health signals that are provided in an easy to consume format, with values ranging from 0-100 on a normalized scale. This leads to a variety of use-cases for the Data Simply DataFeed, for instance, the data can be incorporated into quant, macro and, industry criteria, it can also be used to screen on companies to identify attractive alpha opportunities or monitor portfolio level risk by identifying companies with positive and negative financial sentiment. The table below illustrates the scores available using recent results for Facebook.
Diving deeper into Data Simply’s ESG disclosures data, as can be seen from above, four separate scores are provided: Environmental, Social, Governance, and an overall ESG score.
Three of those scores are categories of sentiment (positive, neutral or negative) that correlate with the number of occurrences of Data Simply’s curated concepts that were disclosed in the company’s financial statements. The fourth score provides an overall financial sentiment for the releases by subtracting the negative score from the positive.
The negative sentiment score can be used as a risk factor to identify companies with financial risk in a portfolio. This data can also be combined with the Data Simply ESG scores to further identify risk as it relates to environment, social and governance issues.