S&P Global Adds Machine-Readable Data Tool for SEC Filings

New York-based data provider S&P Global Market Intelligence has released Machine Readable Filings, the fourth product within its Textual Data suite. The tool cleans and parses data from US Securities and Exchange Commission (SEC) regulatory filings to generate machine-readable text, on which users can then apply natural language processing (NLP) to look for directional indicators of how companies are faring amid the Covid-19 outbreak.

Machine Readable Filings covers about 35,000 companies and was trained using filings dating back to 2006. The product uses the concept of topic modeling, which goes further than looking for whether or not keywords, such as “coronavirus,” appear in a text. It first identifies which SEC-mandated sections the word appears in—for example, in a 10-k filing, it could be in the business overview, risk factors, or management’s discussion and analysis—and then analyzes the N-grams, or the words that follow and precede the keyword.

“It’s one thing for an executive to mention growth margin or net profitability; it’s another thing for them to mention net profit is going up or net profit is declining,” says Kevin Zacharuk, senior product manager for Textual Data.

The new product comes after the data vendor gave hospitals and state and local governments access to Panjiva, S&P Global’s supply chain and trade data tracking platform, on April 2. Using Panjiva, these authorities can track the movements of cargo ships carrying personal protective equipment and ventilators.

Before that, in late March, S&P Global made all of its Covid-19 research, reports, data, and analysis available to the public. Other data providers have made similar decisions, such as Truvalue Labs, which is launching an online, free-to-use Coronavirus ESG Monitor.

The Textual Data suite was launched about 18 months ago. It includes Global Transcripts, which converts unstructured data in management calls into machine-readable format; Textual Data Analytics, which generates sentiment scores, and behavioral metrics based on company transcripts; and a dataset created from an exclusive partnership with Scripts Asia to provide machine-readable transcripts of Japanese investor events. The tools are all available via the Xpressfeed delivery channel.

Warren Breakstone, chief product officer for data management solutions at S&P Global, says the market can expect to see more related releases, adding that the business is “all in” on using applied machine learning and NLP. That was true before Covid-19 gripped the world, but it’s more pressing now.

“Clearly, the markets are very much in turmoil. And what we find in our conversations with our clients now more than ever [is], the numbers alone really don’t provide a complete picture. You really do need the context for those numbers,” Breakstone says.

Plans to bring to market S&P Global Marketplace—a new data platform that will act as a “storefront” for clients to explore and discover datasets from across the S&P Global organization—are on track, and will be officially announced in May.