Researching and analyzing investment opportunities can be challenging for asset management—private equity and hedge fund portfolio managers, researchers, and analysts—because, of course, you want to make sure that you're a good steward of your client's investments.

And when you find and source data, such as traditional or alternative data, you also want to make sure it's reliable and that the methods used to gather it are tried and true.

This article aims to give you an inside look into SESAMm's knowledge graph—one of the key reasons SESAMm's NLP-derived alternative data is reliable and trusted. We'll explain what a knowledge graph is, why it's important, how it works, and what makes SESAMm's knowledge graph unique.

What is a knowledge graph?

A knowledge graph is a digital representation of a network of real-world entities, the foundation of a search engine or question-answering service. This structured data model puts the schema in context through linking and semantic metadata, providing a framework for data integration, analytics, unification, and sharing. In other words, it's like a map and legend, with the legend labeling the concepts, entities, and events and the map connecting and identifying their relationships. These details are stored in a graph database and visualized as a graph representation, hence the term knowledge graph.

Fun fact: The expression, knowledge graph, gained popularity after Google used it in 2012 to name their semantic network.

Two types of knowledge graphs

There are two general types of knowledge graphs: open and private. Open knowledge graphs are open to the public. They're created and made available by organizations such as Wikidata, DBpedia, and Yago. Private knowledge graphs are often only used by organizations that create them, like Google, WolframAlpha, Facebook, and SESAMm (of course). Some offer them up for a fee or subscription, such as Crunchbase and OpenCorporates.

Why a knowledge graph is important

Knowledge graphs are important because they equip us with a model to see how everything relates from a big-picture view, creating new knowledge. Its benefits include:

1. Incorporating disparate data sources, avoiding data silos
2. Integrating structured and unstructured data
3. Revealing insights from hierarchical data
4. Outlining relationships
5. Defining communities

Knowledge graphs inform machine learning algorithms

From a data science and artificial intelligence (AI) perspective, knowledge graphs provide machine-readable details, adding context and depth to data-driven AI techniques such as machine learning. Using knowledge graphs and machine learning models together improves system accuracy and extends the range of machine learning capabilities for better explainability and trustworthiness.

How a knowledge graph works

The core of a knowledge graph is its knowledge model, a collection of interconnected descriptions of concepts, entities, events, and relationships known as an ontology. This model provides a framework for statements or taxonomy. Each statement consists of a subject, predicate, and object (Figure 1)—known as a triple model—and each subject or object is represented only once in the context of the other subjects and their relationships. For example, in this simple sentence, "The boy kicks the ball," The boy is the subject, and kicker is the predicate because he kicks the ball, the object.

Likewise, each statement consists of three components: nodes, edges, and labels. A node, or vertice, represents an entity, which can be anything existing in the real world, such as a person, company, or object. For instance, in this example (Figure 2), Barack Obama is the subject node, Malia and Sasha are object nodes, and the edges, or relationships, are labeled as father or sibling, respectively.

What makes SESAMm's knowledge graph unique?

SESAMm uses open and private datasets with custom, curated information to create our proprietary knowledge graph. As a result, the knowledge graph is a vast map connecting and integrating over 70 million related entities and their keywords, relating each organization to its brands, products, associated executives, names, nicknames, and exchange identifiers in the case of public companies from a data repository made up of more than 18 billion articles and messages and growing.

The knowledge graph is updated regularly

Entities within the knowledge graph are updated weekly and tagged to ensure we correctly track their changes. For instance, the CEO of a company today might not be its CEO tomorrow. And brands might be bought and sold, changing the parent company with each sale. So, weekly updates within the knowledge graph ensure the system is aware of these changes.

NLP-driven accuracy

At SESAMm, named entity disambiguation (NED), a natural language processing (NLP) technique, identifies named entities based on their context and usage. Text referencing "Elon," for example, could refer indirectly to Tesla through its CEO or to a university in North Carolina. Only the context allows us to differentiate, and NED considers that context when classifying entities. This method is superior to simple pattern matching, which limits the number of possible matches, requires frequent manual adjustments, and can't distinguish homophones.

SESAMm uses three other NLP tools to identify entities and create actionable insights: lemmatization, embeddings, and similarity. The lemmatization process normalizes a word into its base form (morphology) to help identify and aggregate entities. Embedding assigns the entity a numerical value to help analyze how words change meaning depending on context and understand the subtle differences between words that refer to the same concept. Similarity measures whether two words, sentences, or objects are close to one another in meaning.

Learn more: “Gain Insights Fom Financial and ESG Data Using AI: A Comprehensive Guide.”

How SESAMm's knowledge graph benefits you

SESAMm tailored its knowledge graph to find, extract, and analyze data about public or private entities, which isn't readily available from the web or standard rating firms. This unique implementation of a knowledge graph provides insights to give you an edge when researching, analyzing, and submitting recommendations to the portfolio manager or clients.

SESAMm's premiere platform, TextReveal®, allows you to leverage NLP-driven insights fully and receive high-quality results through data streams, modular API and dashboard visualization, and signals and alerts. It's perfect for many quantitative, quantamental, and ESG investment use cases.

Learn how SESAMm can support you in your investment decision-making and request a demo today.

November 11, 2022, FTX, a $32 billion cryptocurrency exchange company that many believed would “change the world,” filed for bankruptcy. This news shook the crypto and financial communities, compelling many to debate the future of the crypto market and its platforms.

How did FTX collapse?

You could say that FTX’s collapse began before the news broke, but here’s a summary of events as The New York Times and ABC News details:

Breaking news

In early November, CoinDesk, a crypto publication, broke the news on a leaked document from FTX. The balance sheet showed that the hedge fund run by Sam Bankman-Fried (SBF), Alameda Research, held a substantial amount of FTT tokens. In short, SBF had set up Alameda (his trading firm) and FTX (his exchange firm) in such a way that if one unit experienced trouble, such as dropping cryptocurrency prices, the other experienced it, too.

First domino falls

By the way, FTT is used for various functions, including traders’ payment of operation fees. Also, by the way, Changpeng Zhao, Binance’s Chief Executive, sold his stake in FTX to SBF in 2021, partially with FTT. So, “due to recent revelations,” Binance (Zhao) announced on November 6, 2022, that it would sell its FTT tokens.

Other dominos follow

Traders responded; they hurried to pull funds out of FTX out of fear, and FTT’s price fell. Meanwhile, FTX processed withdrawal requests over three days, amounting to an estimated $6 billion. The liquidity crunch was upon it.

Then, on November 8, Binance said it would bail out FTX. But on November 9, Binance backtracked and announced in a Tweet that it would not “as a result of corporate due diligence,” while also citing regulatory investigations and reports of mishandled funds.

Things get worse

The next day, November 10, the Securities Commission of the Bahamas froze FTX’s assets, citing the public statement about potentially “mishandled” and “mismanaged” customer funds. On November 11, FTX filed for Chapter 11 bankruptcy protections, and SBF resigned as CEO. John J. Ray III—famously known as the CEO who headed the infamously known energy company, Enron, through its collapse in the 2000s—replaced SBF on November 17.

Fallout

Today, FTX faces federal investigation for securities laws violations based on a report by The Wall Street Journal regarding FTX lending customer deposits to Alameda Research for liabilities, of which the company’s top executives were aware. Investors have suffered loss, traders have suffered loss, and the greater crypto community and regulators are asking questions.

FTX and SBF web data analysis

News about FTX’s collapse generated tons of web data for us to scour. With this data, here’s what we aimed to find out:

• How did the public web react to FTX’s collapse?
• Could we have seen red flags before the news broke?
• What was FTX’s collapse’s effect on the cryptocurrency market’s sentiment?
• Is it possible to evaluate cryptocurrency exchange companies’ ESG risks and opportunities?
• Was FTX’s collapse unprecedented? If not, what does web data tell us about that?

FTX and Sam Bankman-Fried mentions analysis

Web public sentiment for FTX and SBF was consistently positive until Q1 of 2022. As mentions volume increased, their sentiment polarity decreased (Figure 1). The mentions spike for both in November when CoinDesk broke the news. Likewise, polarity dips into the negative range for both.

Definition: Polarity represents the aggregate of positive and negative sentiments (opinions or reviews) on a company. A 0 score means there is as much positive as negative sentiment expressed. The dotted and dashed lines represent sentiment in the following charts.

Looking closer at Q1 (Figure 2), we find that mentions affecting sentiment increased for FTX and SBF during this period. What are the mentions about, and why did they affect polarity negatively?

It turns out that SBF is linked to other keywords—we call these co-mentions—and between January 2022 and November 2022, SBF/withdrawal co-mentions (Figure 3) spiked in July when SBF defended Terra Luna’s founder, who was accused of peddling a Ponzi scheme.

If withdrawal co-mentions brought up possible reasons why SBF and FTX experienced dips in sentiment, what other co-mentions could give us more insight? How about donations, SEC, and U.S. elections?

Bankman-Fried has exhibited patterns of making political statements, attempting to influence crypto regulations, and donating funds before elections. It should be no surprise that SBF’s co-mentions with C-level unethical practices yield additional data.

Note: To see the co-mentions with unethical practices chart, contact a SESAMm representative today.

Sam Bankman-Fried ESG risk analysis

Corporate governance stands out when evaluating SBF’s ESG risks, but his social risks are nothing to ignore either.

Two areas of governance risks to note are money laundering and board of directors (Figure 5). Money laundering as a co-mention has been an issue as early as February 2022, but it became a bigger issue in October. These risks may be popping up due to allegations of manipulating the price of the APT token and a securities violations probe.

Note: To see the social risks over time chart, contact a SESAMm representative today.

FTX and crypto market web data analysis

If you’ve read this far, you by now get an impression of FTX and SBF, from mention volume to sentiment analysis and ESG risk. But how did FTX’s collapse affect the overall cryptocurrency market? Let’s find out.

In comparing the sentiment polarities for FTX and the crypto market from January 2021 through November 2022 (Figure 6), the sentiment for crypto remains relatively steady despite FTX’s sentiment taking a hit.

When comparing other cryptocurrency exchanges to FTX (Figure 7), sentiment polarity for them is hardly affected, except Binance, because of its connection with FTX. Oddly enough, eToro experienced a boost in sentiment, possibly because of its core values around openness and transparency, the fact that they’ve been around since 2007, its early compliance with regulations (i.e., AMF, FCA, ASIC, BaFin, and ACPR), and that it also proposes investing in stocks and ETFs, a contrast to most other crypto market exchanges. Bitfinex has its own issues, so its dip in sentiment might not be correlated.

At this time, FTX’s ESG risks based on the mention volume are only surpassed by Bitfinex (Figure 8), which its risks are based on many other reasons we won’t get into in this article.

Note: To see a comparison chart of social and governance risks for each exchange, contact a SESAMm representative today.

Centralized vs. decentralized crypto exchange platforms

FTX’s collapse also affected sentiment around the centralized vs. decentralized debate. Since October 2022, sentiment for centralized exchange platforms, such as FTX and its competitors, has fallen (Figure 9).

Likewise, the mention volume for self-custody has more than doubled in the last couple of months (Figure 10). Although centralized platforms offer quicker and easier access to crypto trading, traders are considering complex but more secure options such as crypto wallets and keys because, like banks, centralized exchanges can do what they will with cryptocurrency while it’s in their possession. With self-custody, owners are in control.

Note: To see additional charts, such as competitive data share for crypto wallets, contact a SESAMm representative today.

FTX not the first exchange collapse

Believe it or not, FTX was not the first crypto exchange to collapse. In 2014, Mt. Gox—the biggest crypto exchange at the time—lost half a billion dollars worth of Bitcoin due to a hack. How did Mt. Gox’s collapse affect sentiment for the crypto market then? The short answer is: It didn’t.

Figure 11 shows that while Mt. Gox’s sentiment polarity fluctuated, even reaching negative territories, the sentiment for the crypto market remained relatively stable and positive.

Is FTX’s collapse a warning for investors?

Our analysis is that investors should treat cryptocurrency exchanges like any investment opportunity. Do your due diligence and monitor your portfolio with tools like SESAMm’s TextReveal®.

As for the cryptocurrency market, data shows that sentiment for it remains level and positive. We speculate that cryptocurrency and centralized exchanges are here to stay. However, based on historical data and current news, we suspect conversations about crypto regulations to increase.

Reach out to SESAMm

For a deeper analysis of FTX’s collapse and access to all charts and supportive-article links, reach out to a representative today.

In our recent webinar titled "ESG Controversies: A Comparative Study of the Public and Private Sectors," Sylvain Forté, CEO, and Alexandre Tiesset, Head of ESG, explored the transformative impact of Artificial Intelligence (AI) on understanding and evaluating ESG controversies, especially in the context of public versus private sectors. This in-depth discussion provided unique insights into the challenges and opportunities presented by ESG data analysis.

One of the primary challenges highlighted was the disparity in data availability between public and private companies. Public entities are subject to stricter disclosure requirements, which often results in a wealth of data facilitating ESG assessment. In contrast, the opacity of private companies complicates the evaluation of their ESG performance, creating a demand for innovative solutions to ensure equitable and accurate comparisons across the investment spectrum.

SESAMm, with its pioneering AI-powered text analysis tool TextReveal, stands at the forefront of tackling these challenges. By analyzing billions of documents, TextReveal extracts crucial ESG insights, addressing the data scarcity in the private sector and enabling a more nuanced understanding of ESG controversies.

The webinar underscored the importance of data normalization to counteract biases, allowing for more precise comparisons across sectors and companies. With the help of AI, SESAMm can conduct analyses across a vast number of entities, offering investors a comprehensive view of potential risks and controversies.

The Ikea case study served as a prime example of SESAMm's capability to perform deep dives into specific companies. The analysis revealed Ikea's slightly higher environmental controversies than the consumer discretionary sector average, including accusations of greenwashing related to deforestation. On the social front, Ikea faced challenges with product safety, human rights breaches, data leaks, and privacy violations, such as the 2021 lawsuit against Ikea France for alleged privacy violations of staff.

Furthermore, the webinar touched on the challenges Ikea faces under specific Sustainable Development Goals (SDGs), including health and well-being (due to product recalls and workforce health concerns), Sustainable Cities, and Responsible Consumption and Production. Despite these issues, Ikea shows fewer problems related to industry innovation and infrastructure, and peace, justice, and strong institutions, indicating areas of better risk mitigation.

In conclusion, the integration of AI into ESG evaluation marks a significant advancement in investment analysis. As the demand for sustainable investment options grows, the need for sophisticated tools to analyze ESG controversies becomes increasingly evident. The webinar's insights highlight AI's potential to enhance our understanding of ESG risks and opportunities, paving the way for more responsible investing.

Watch the webinar replay now:

Dive deeper into ESG controversies and uncover strategies for navigating these challenges effectively. Download "ESG Controversies: A Comparative Study of Public vs Private Sectors" and equip your organization with the insights needed to enhance your ESG practices for a sustainable future. Fill out the form below to access your copy and lead the way in corporate sustainability.

Reach out to SESAMm

TextReveal's web data analysis of over five million public and private companies is essential for keeping tabs on ESG investment risks. To learn more about how you can analyze web data or request a demo, contact one of our representatives.