Eric Fischkin
Dr. Richard Peterson
- Using proprietary and fine-tuned LLMs to measure specific emotion and sentiment classifications for each sentence, speaker, and document.
- Identifying 1,000+ topics, 4,000+ event types, and references to millions of products, people, and organizations in each transcript.
- Potential use cases include alpha generation, ESG research, and downside risk management.
A CEO discusses on a quarterly earnings call what he believes the coming 12 months will bring. He mentions supply chain and manufacturing challenges, price pressure caused by inflation, and the most recent marketing campaign. Is the CEO optimistic or pessimistic about each topic? What do analyst reactions suggest is most likely to impact the company’s stock performance?
Traditionally, institutional investors and quantitative firms have judged this themselves, intuitively. By using prepared transcripts and an LLM to measure the tones expressed by the CEO, this product removes potential human bias and enables users to scale sentiment analytics quantitatively, offering innovative approaches to finding alpha.
Advanced earnings call analytics
LSEG MarketPsych Transcript Analytics is a new refined data feed that brings together LSEG’s data and MarketPsych’s natural language processing (NLP) capabilities. MarketPsych develops AI-based solutions to extract actionable analytics from financial text. LSEG and MarketPsych have a nearly 15-year partnership, which delivers sentiment and thematic data feeds, ESG analytics, NLP tools, and predictive models to financial services firms in more than 25 countries.
Based on LSEG Transcripts data – which covers more than 16,000 public companies around the globe – Transcript Analytics utilises some of the most advanced data and LLM technology available. In addition to 1,000+ prepared topics, the free text search in the API reveals unlimited phrases and topics for search and sentiment tagging. The data is exceptionally granular, with the analytics solution publishing time references, verb tenses, parts of speech and other nuances, alongside a total of 13 speaker emotions. In addition, MarketPsych’s fine-tuned roBERTa-based classifiers are the most accurate classifiers available. roBERTa is an approach for pre-training natural language processing systems developed by Meta AI, which itself builds on the BERT learning model developed by Google AI. Users can unlock the power of this high precision and granularity with custom API queries on historical and real-time data. The API allows unique research, rapid testing, and seamless deployment of data feeds into production.
Exploring the use cases
With this innovative analytics solution applied to LSEG’s call transcript data, a wide range of potential use cases emerge. When looking across all U.S. companies, firms with high levels of sentiment (top 10%) measured during their earnings calls have significant next month stock price outperformance versus lower sentiment stocks. This effect is even more pronounced for companies expressing high levels of optimism. Investors can use Transcript Analytics to systematically select equity investments based on this type of correlation, or they can incorporate the results of Transcript Analytics into their own models.
In another use case, the addition of an ESG classifier in Transcript Analytics provides monitoring capabilities. In one MarketPsych study, the share prices of the 10% of companies with the lowest ESG sentiment scores during their earnings calls underperform their peers over the next month, providing an early warning for investors. Also, an analyst can search for key ESG phrases such as “carbon”, “climate” or “emissions”. The analytics will show the number of times the term has been mentioned, and the positive or negative ESG sentiment each time the term is used, as well as overall over a period. In addition, users can drill down to see the sentence in which the search term is mentioned.
Transcript Analytics can also be deployed for risk management. Transcript Analytics quantifies how corporate executives increase or decrease mentions and sentiment of key topics and entities. For example, the analytics tag key negative terms across selected companies such as “fines”. The analytics identify the companies in an industry with the most negative sentiment over a defined period. One MarketPsych study found that companies with high levels of the emotion “disapproval” (top 5%) expressed during their calls experienced significant stock price underperformance the following month. This kind of information about companies is useful for third-party risk management, as well as for managing credit risk.
These are just a sample of three use cases – there are many more ways that this solution can be deployed by institutional investors and quantitative firms to identify potential opportunities in corporate calls over time and at scale.
Legal Disclaimer
Republication or redistribution of LSE Group content is prohibited without our prior written consent.
The content of this publication is for informational purposes only and has no legal effect, does not form part of any contract, does not, and does not seek to constitute advice of any nature and no reliance should be placed upon statements contained herein. Whilst reasonable efforts have been taken to ensure that the contents of this publication are accurate and reliable, LSE Group does not guarantee that this document is free from errors or omissions; therefore, you may not rely upon the content of this document under any circumstances and you should seek your own independent legal, investment, tax and other advice. Neither We nor our affiliates shall be liable for any errors, inaccuracies or delays in the publication or any other content, or for any actions taken by you in reliance thereon.
Copyright © 2024 London Stock Exchange Group. All rights reserved.
The content of this publication is provided by London Stock Exchange Group plc, its applicable group undertakings and/or its affiliates or licensors (the “LSE Group” or “We”) exclusively.
Neither We nor our affiliates guarantee the accuracy of or endorse the views or opinions given by any third party content provider, advertiser, sponsor or other user. We may link to, reference, or promote websites, applications and/or services from third parties. You agree that We are not responsible for, and do not control such non-LSE Group websites, applications or services.
The content of this publication is for informational purposes only. All information and data contained in this publication is obtained by LSE Group from sources believed by it to be accurate and reliable. Because of the possibility of human and mechanical error as well as other factors, however, such information and data are provided "as is" without warranty of any kind. You understand and agree that this publication does not, and does not seek to, constitute advice of any nature. You may not rely upon the content of this document under any circumstances and should seek your own independent legal, tax or investment advice or opinion regarding the suitability, value or profitability of any particular security, portfolio or investment strategy. Neither We nor our affiliates shall be liable for any errors, inaccuracies or delays in the publication or any other content, or for any actions taken by you in reliance thereon. You expressly agree that your use of the publication and its content is at your sole risk.
To the fullest extent permitted by applicable law, LSE Group, expressly disclaims any representation or warranties, express or implied, including, without limitation, any representations or warranties of performance, merchantability, fitness for a particular purpose, accuracy, completeness, reliability and non-infringement. LSE Group, its subsidiaries, its affiliates and their respective shareholders, directors, officers employees, agents, advertisers, content providers and licensors (collectively referred to as the “LSE Group Parties”) disclaim all responsibility for any loss, liability or damage of any kind resulting from or related to access, use or the unavailability of the publication (or any part of it); and none of the LSE Group Parties will be liable (jointly or severally) to you for any direct, indirect, consequential, special, incidental, punitive or exemplary damages, howsoever arising, even if any member of the LSE Group Parties are advised in advance of the possibility of such damages or could have foreseen any such damages arising or resulting from the use of, or inability to use, the information contained in the publication. For the avoidance of doubt, the LSE Group Parties shall have no liability for any losses, claims, demands, actions, proceedings, damages, costs or expenses arising out of, or in any way connected with, the information contained in this document.
LSE Group is the owner of various intellectual property rights ("IPR”), including but not limited to, numerous trademarks that are used to identify, advertise, and promote LSE Group products, services and activities. Nothing contained herein should be construed as granting any licence or right to use any of the trademarks or any other LSE Group IPR for any purpose whatsoever without the written permission or applicable licence terms.
