In 2018, the global unemployment rate was at 5 percent, down from 5.6 percent in 2017, 5.9 percent in 2009 and 6.4 percent in 2000. Although the unemployment rate has recovered since the global economic crisis, unemployment remains widespread in some regions. Furthermore, companies can take advantage of employee rights. To ensure that employees are treated fairly, the Fair Labor Standards Act (FLSA) was established to ensure rights on minimum wage, overtime pay, and youth employment standards for employees in the private sector and in Federal, State, and local governments. As environmental, social, governance factors continue to motivate investors into placing their money in companies that are in line with their morals and values, AI can help investors identify corporate ESG practices.
Employees suffer from uncertainty, irregular and lower wages, longer working hours, absence of collective bargaining and representation rights, and often have ambiguous or disguised employment statuses. Their physical and financial vulnerability are increased due to organizations excluding benefits such as social security schemes, safety and health, maternity leave, and other labor rights that protect employees. Additionally, 152 million children are still in child labor, 40 million people are in different forms of forced labor and forced marriage, and countless people are excluded from learning opportunities due to discrimination by sex, age, disability, ethnicity, and political and/or religious affiliations.
How can investors and financial institutions understand which companies have fair labor practices? With the wealth of data from news sources, blogs or other public data, early warning signals can be identified from companies that are involved in a series of anomalous labor practices. These insights would assist investors or asset managers in assessing risk and in making less under-informed decisions.
Identifying companies with fair labor practices
With the wealth of data from news sources, blogs or other public data, early warning signals can be identified from companies that are involved in a series of anomalous labor practices. These insights would assist investors in assessing risk and in making more-informed decisions.
Investing in companies with strong ESG practices not only appeal to individuals’ moral compasses, but 90 percent of more than 2,200 individual studies reveal that the business cases for ESG investing are well-founded. Furthermore, the report by the Journal of Sustainable Finance and Investment shows that there is no negative correlation between ESG and corporate financial performance. As demand grows for sustainable investing or investing in companies with high ESG scores, the use of Artificial Intelligence (AI) to gather useful data on companies with strong sustainability, social impact, and governance practices will be paramount to recognizing companies that are committed to making a positive impact between those those that are looking for quick gains.
Tracking companies’ financial results, annual reports, news and social media posts are some ways that investors may currently follow a corporation’s ESG practices today. But the use of AI to gather alternative data, takes this investment practice to an entirely new level as it significantly increases capabilities to track more companies, find crucial information that may be hidden, and analyze the sentiment of data.
AI and NLP are used today by large hedge funds, investment firms, and others in the financial services industry including Goldman Sachs, Allianz, Barclays, and JP Morgan. Within the next five years AI’s innovative solutions will be readily available to smaller financial firms and even retail investors.
Using AI to reveal corporate labor practices
Accern is a no-code AI platform that provides an end-to-end data science process that enables data scientists and analysts at financial organizations to easily build models that uncover investment and risk signals and trends from vast amounts of data. Using the Accern AI Platform we can build a use case, which can track and identify companies in the S&P500 with positive and negative labor practices.
AI Use Case Setup
Observation Period: January 1st, 2020 to June 30th, 2020
Data Sources: Public News and Blogs
Company: All in the S&P 500 companies
ESG Issues: Social – Labor Practices
AI Model: Accern ESG NLP Model
Once the model is deployed, the results of the ESG model are available through an API, visual dashboard, or in a Jupiter Notebook based on the user’s preference. The results are portrayed in a way that investors can use the analyses and easily come up with next action steps (see below).
Taking a look into companies’ labor practices, the graphic above shows how data is consolidated and then analyzed. The number of signals refers to the number of “hits” or “mentions” about labor practices. The number of stories is equal to how many unique stories there are on a company’s labor practices. The number of entities include all of the companies in the S&P 500 that fit the labor practice description. Lastly, the number of events is one because we are only looking into companies” labor practices.
Interpreting the graphic further:
- There were 120 entities (unique companies) in the S&P 500 which mentioned Labor Practice activities during the observations period.
- Additionally, there were 135 stories/documents which contained mentions of employment discrimination, child labor, fair labor standards, labor law violations, employee harassment directly related to the company.
- Within the 135 stories, 3364 signals were identified (a story may have multiple signals), where a signal is a text snippet that mentions a Labor Practices event and the respective company (or variation of the company name, product, leadership or subsidiary).
- However, of the 135 stories only 62 stories were unique. Accern uses an algorithm which identifies and clusters stories which have been republished or are contextually about the same topic and company.
The graph below shows the data sources. Users have the opportunity to choose specific sources that are credible to the event such a local newspaper or credible sources.
Note: For this case study, only a subset of Accern’s news feeds were used.
Labor Practice Signals
The following graph shows the volume of Labor Practice signals across the observation period of January 1st, 2020 to June 30th, 2020.
There are spikes in labor practice signals from early February and May indicating increased activities around labor practice topics than the average norm. Next, we will be able to observe which companies are mentioned in regards to labor practice activities over the observation period.
Sector Signal Story table
This graph shows which industries and sectors had the most signals on companies with labor practices.
From the insights, we can identify which sectors have the warning signals of labor practice issues the top four sectors include Services, Technology, Transportation and Industrials.
Drilling down further we can identify the specific companies in the S&P500 with potential labour practice issues. For example, United Continental Holdings, Inc., is has a high number of signals (549) as there are also discussions around Labor Practice activities with a strong negative market perception.
ESG Labor Practice Signal Key Terms/Themes
The graph below shows some of the topics being mentioned around labor practices during the observation period.
The immediate intuition based on the key terms from the generated signals is that there are several issues related to minimum wage, child labor, migrant works, and labor unions that could indicate a hidden trend among certain industries or companies. Digging into the insights further could reveal a number of warning signals that reveal insights into specific industries’ or companies’ labor practices.
We can drill into the supporting arguments and documents as shown in the image below.
Accern’s No-Code AI platform is able to extract the key passages from full documents and understand the underlying details of the warning signals generated. Additionally, users can analyze the sentiment of each documents with our adaptive NLP models to identify whether there is a positive, neutral, or negative connotation with the news or company.
Using the Accern AI Platform ESG Investment teams can rapidly conduct top-down or bottom-up ESG analysis when building investment signals or a sustainability thesis on a company, sector or region.
How users can customize the Accern Platform
Users can quickly extend and customize the analysis on Accern’s platform by
- Adding additional content sources from the integrated datastore.
- Building additional ESG themes to track.
- Adjusting the NLP model and the parameters of the analysis.
- Comparing the impact of ESG activities across companies, industries and sectors.
- Identifying which companies have related or co-mentions and the market perception.
- Understanding ESG warning signals and critical insights
Business applications of the ESG model
Customers currently use the ESG model for:
- Idea Generation and Surveillance: To identify and monitor investment opportunities within the ESG space in real-time.
- Risk and Compliance: To uncover risks and early warning signals within the ESG space.
- Company Research: To improve initial searches by eliminating noise and focus on the core aspects of analysis within ESG.
- Building Alpha Trading Strategies: To build factor models and investment signals using ESG data.
For more information on ESG, how ESG scores are calculated, and how NLP can identify ESG events download our one pager ESG cheat sheet.
Accern is a no-code AI platform that provides an end-to-end data science process that enables data scientists at financial organizations to easily build models that uncover actionable findings from structured and unstructured data. With Accern, you can automate processes, find additional value in your data, and inform better business decisions- faster and more accurately than before. For more information on how we can accelerate artificial intelligence adoption for your organization, visit accern.com