Companies that are Positive and Transparent on Earnings Calls Tend to Outperform their Peers, According to New S&P Global Market Intelligence Analysis

News provided by

Jan 31, 2020, 09:00 ET

NEW YORK, Jan. 31, 2020 /PRNewswire/ -- Firms that use a greater number positive words to describe their financials during an earnings call tend to outperform their peers' stock price by approximately 9%, according to a new analysis conducted by S&P Global Market Intelligence.

The new report titled, "Natural Language Processing – Part III: Feature Engineering," found that executives of companies within the Russell 3000 who frequently articulate references to growth and expansion-related descriptors on revenue, earnings or profitability outperform their counterparts by 6-9% per year.

Led by S&P Global Market Intelligence's Quantamental Research team, the research applies natural language processing (NLP) through S&P Global Market Intelligence's Textual Data Analytics (TDA) technology to analyze the tone, complexity, frequency of mentions and transparency of more than 2,400 companies earnings call transcripts from January 2008 through December 2017.

Other key findings from the report include:

Firms whose executives referenced the most instances of guidance outperformed their peers by nearly 6%.
Companies with leaders who used the most similar language between quarterly earnings calls outperformed their peers by nearly 4%.
Firms with executives who introduce numerical values earlier in the call outperformed their peers by nearly 4%
Company leaders who avoid blaming external circumstances on their results outperformed their peers by approximately 2%.

"Deep analysis of the unstructured data within corporate earnings call demonstrates how highlighting positivity and transparency within prepared remarks can unveil key signals useful for generating alpha," said David Pope, Managing Director of Quantamental Research at S&P Global Market Intelligence. "As unstructured data is being created at a historic pace, there's an opportunity to continually utilize and evolve technologies such as machine learning and natural language process to bring new insights to the markets."

"Part III: Feature Engineering" is the third report in the "Natural Language Processing" research series, the first paper titled, "Natural Language Processing – Part 1: Primer" followed by "Natural Language Processing – Part 2: Stock Selection" published in 2017 and 2018 respectively. The series was undertaken by S&P Global Market Intelligence's Quantamental Research team to demystify many aspects of NLP by providing concrete illustrations of how the technology can be used to quantify the sentiment of earnings calls.

To request a copy of the full study, please visit our website here or reach out to Amanda Oey at [email protected].

About S&P Global Market Intelligence
At S&P Global Market Intelligence, we know that not all information is important—some of it is vital. We integrate financial and industry data, research and news into tools that help clients track performance, generate alpha, identify investment ideas, understand competitive and industry dynamics, perform valuations and assess credit risk. Investment professionals, government agencies, corporations and universities globally can gain the intelligence essential to making business and financial decisions with conviction.

S&P Global Market Intelligence is a division of S&P Global (NYSE: SPGI). For more information, visit www.spglobal.com.

SOURCE S&P Global Market Intelligence