Screen smarter. Act faster. Flag hidden risks at scale.

Speed and accuracy are critical in due diligence, especially when screening for reputational or compliance risks across large portfolios. That’s why we built SESAMm’s Secondaries & Credit Screening report: a faster, smarter way to assess exposure to restricted and controversial business activities.

How it works

Designed for investors, compliance teams, and financial institutions, this report uses SESAMm’s generative AI and large language models (LLMs) to analyze millions of documents and flag companies involved in sensitive sectors.

With just a list of company names, it highlights potential involvement in:

• Fossil Fuels & Nuclear
• Weapons & Military Equipment
• Predatory Lending
• Gambling & Betting
• Adult & Violent Content
• Severe Human Rights & Labor Violations
• Tobacco, Alcohol & Recreational Drugs

Each result includes linked sources and a clear explanation, providing not just a flag but the context behind it.

Fast, Transparent, Scalable

Whether you're conducting secondary deal due diligence, reviewing a loanbook, or aligning portfolios with exclusion lists, this new report offers:

• Scalable, fast batch screening: Upload a list of companies and get standardized, structured results in minutes.
• Transparency: Each flag is backed by a justification and includes access to cited sources.
• Faster decisions: Get standardized Excel outputs in minutes.
• Deeper insight: Uncover risks that go beyond traditional industry classifications.

A New Standard for Risk Screening

Already in use by leading financial firms, the Secondaries & Credit Screening report brings clarity to complex decisions, helping teams flag risks earlier, faster, and more confidently.

Ready to Get Started?

Reach out to see a sample report or request a custom screening of your own list. With SESAMm’s Secondaries & Credit Screening, your next due diligence process just got faster and smarter.

One of the biggest challenges in risk monitoring is sifting through mountains of irrelevant data. Whether you're using search engines, financial news platforms, or even specialized in-house analytics, you end up with too much noise. Scrolling through to page 12 of Google is not only time-consuming, but leaves you with the nagging feeling that you could still be missing something.

Artificial Intelligence (AI) is a hot topic, with new breakthroughs and possible applications popping up every day. The question is no longer simply “can AI help me with that?” but rather “how can I use AI to help with that?” For Environmental, Social, and Governance (ESG) controversy and risk monitoring, AI is used to sift through enormous data sets at unparalleled speeds, bringing critical insights to the forefront faster and more efficiently than humanly possible.

When there are hundreds of companies to monitor, for example in a large investment portfolio or a group of suppliers, the advantages of AI are obvious. But what about smaller portfolios? How do you know it’s time to start using AI? Based on our experience working with private equity firms, asset managers and commercial banks, we’ve pulled together five signs that it’s time to consider AI.

1. Overwhelmed by Data: There's Too Much Noise

An AI-powered tool filters out the noise, even in situations where seemingly only humans would be able to do it, giving you the peace of mind that there’s no controversy lurking in the dark corners of the web. All of the key information is gathered in one place, ready for you to evaluate and decide the best course of action.

2. Difficulty Finding Critical Information: The Black Hole of Private Companies

On the flip side - sometimes instead of finding too much data, you can’t find any data at all. For private companies, information can be scarce, especially for smaller companies based overseas, where the only news coverage is local and in the local language. In this case, ESG ratings agencies often aren’t able to fill the gap either. There are millions of firms worldwide and less than 50,000 of them are covered by rating agencies (source).

AI, on the other hand, enables systematic coverage and statistically relevant results without human intervention, analyzing millions of websites and providing coverage on millions of public & private companies. If you are struggling to find information on a company, AI might be the answer.

3. Can't Accurately Analyze an Event: The Context is Missing

Beyond the actual controversy or event itself, understanding the context and history around it is essential for risk assessment. Is this a one-off concern or part of a recurring pattern? To get the full picture, you need to take a closer look not only at the company in question, but the key players, i.e. key executives, and the industry as a whole to understand if this is within the norms.

AI has an important role to play here also. By simply expanding the search, AI can provide you with a full picture of the controversy, including a quick summary and a benchmark against competitors in just a matter of minutes.

4. Missed Critical Window for Action: The Cost of Inefficiency

Markets can change quickly - and it’s only getting worse as information is spreading faster and more widely. The more time it takes you to gather and analyze information, the less time you have to react. This can be a challenge whether you are monitoring 30 companies or 100’s. If you find yourself trapped in a cycle of reacting to news rather than acting proactively, AI can help. Because AI scans and analyzes information in seconds, the alerts to potential controversies are in near real-time, allowing you as much time as possible to take action.

5. Missing ESG Expertise: The Knowledge Gap

To top it all off, ESG is complex and constantly evolving. Understanding what data is relevant and how to evaluate it requires real expertise. ESG rating agencies provide some guidance, but they typically leverage self-reported data - which is naturally biased. Take greenwashing for example where a company misleads its stakeholders, investors, and consumers about its environmental practices by communicating positive environmental performance contrary to its actual, less positive execution. It’s difficult to identify greenwashing using self-reported data.

Because AI relies on external stakeholders, such as online forums or news sources, it offers an unbiased take on a company’s ESG performance. Additionally, by choosing an AI with ESG expertise built-in, you benefit from an expert analysis without increasing the burden on your team.

As the speed and amount of information available continues to grow, AI offers a scalable way to monitor your partners, suppliers and portfolio. To learn more and find out if AI is a good fit for your company, contact our experts at SESAMm.

Environmental, Social, and Governance (ESG) factors have moved from the periphery to the core of investment and risk management discussions. While positive ESG actions are often linked to better financial stability, new research from the Norwegian University of Science and Technology reveals the flip side: ESG controversies significantly increase a company’s exposure to systemic risk.

Published in Finance Research Letters (2025), the study "Environmental, Social and Governance Controversies and Systematic Risk: A Machine Learning Approach" sheds new light on the complex relationship between ESG controversies and firm-level risk, using advanced machine learning (ML) techniques to provide unprecedented insights.

What the Study Examined

The researchers analyzed 463 non-financial companies listed in the STOXX Europe 600 index between 2016 and 2022. Their objective was to assess whether ESG controversies, such as environmental violations, social misconduct, or governance failures, impact a company’s systematic risk, measured by its beta coefficient (a key risk indicator in finance).

Importantly, the study leveraged a Random Forest machine learning model combined with Explainable AI (XAI) methods to predict and interpret firm-level risk.

Key Finding: ESG Controversies Increase Systematic Risk

The study's core conclusion is clear: ESG controversies significantly raise a firm’s systematic risk. In other words, when a company is embroiled in environmental scandals, social misconduct, or governance failures, investors perceive it as riskier, leading to greater stock volatility and sensitivity to market shocks.

Not All Controversies Are Equal

As Responsible Investor has reported, some investors have already voiced their concerns.

Sondre Myge, head of ESG at Skagen Funds, said that while it’s still early, his “first impression is that it complicates comparability. Investors are now drowning in a mix of voluntary and legal disclosures requiring them to make assessments through a kaleidoscope of standards and methodologies. Sifting critically through hundreds of pages of text just for one company is a huge undertaking. While first movers will provide glossy reports that convey a convincing impression, it is important to remember that disclosures are not necessarily representative.”

Jan Kaeraa Rasmussen, head of ESG and sustainability at PensionDanmark, agreed, stating that initial disclosures tend to be “more narrative than quantitative. This limits our ability to draw robust, forward-looking insights from the information provided.”

What’s Next: Simplification or More Complexity?

Interestingly, the study found that the relationship between ESG controversies and risk is non-linear:

• Firms experiencing their first ESG controversy ("first-timers") see a pronounced jump in risk.
• For firms regularly facing controversies ("regulars"), the effect on risk remains high but stabilizes.
• Small controversies matter most for firms with otherwise clean records. For already controversial
• firms, additional issues have less incremental impact.
  

This pattern aligns with investor behavior: markets tend to overreact to initial controversies while becoming desensitized to repeated issues.

Machine Learning: A Powerful Risk Prediction Tool

The researchers used Random Forest regression, a machine learning technique that captures complex, non-linear relationships in data, to predict systematic risk.

Compared to traditional models, the Random Forest approach reduced the prediction error by nearly 30%. The model achieved a mean absolute error of 0.25 for 2022 risk predictions, outperforming a naïve benchmark model that assigned every company the same average risk.

This reinforces the value of machine learning in financial risk management — particularly when assessing non-traditional factors like ESG controversies.

Industry Matters: Some Sectors Are More Vulnerable

The study also highlights that the impact of ESG controversies on risk is highly sector-specific.

Industries with Highest Sensitivity to ESG Controversies:

• Machinery
• Oil, Gas & Consumable Fuels
• Chemicals
• Metals & Mining
• Professional Services
  

These industries tend to face greater investor scrutiny due to their environmental footprint or governance challenges.

Industries with Lowest Sensitivity:

• Real Estate
• Food Products
• Electric Utilities

The lower sensitivity in these sectors may reflect stronger sustainability practices, regulatory protections, or reduced operational exposure to ESG risks.

Geographic Differences in Risk

In addition to industry effects, the research found that firms in certain countries face higher systematic risk linked to ESG controversies.

Countries with the highest predicted systematic risk included:

• Finland
• Portugal
• Poland
• Netherlands
• Sweden

Meanwhile, firms in Italy and Germany showed lower ESG-related risk exposure.

Implications for Investors, Risk Managers, and Companies

This study provides clear takeaways for finance professionals and ESG practitioners:

1. ESG Controversy Monitoring Is Critical
   Investors need advanced ESG monitoring tools to detect early signs of controversy, particularly for first-time incidents, which have the highest risk impact.
2. Tailor Risk Management to Industry
   Risk managers should take into account industry-specific vulnerabilities.
3. Machine Learning Enhances Risk Prediction
   Traditional risk models may overlook non-linear ESG effects. Machine learning offers a powerful, data-driven approach to anticipate market reactions to ESG incidents.
4. Proactive ESG Management Reduces Risk
   Companies should address ESG risks early before they escalate into high-profile controversies that damage reputation and investor trust.
   

Conclusion

This groundbreaking research bridges ESG and AI, demonstrating that ESG controversies are not just a reputational issue; they are a quantifiable financial risk. Machine learning models provide finance professionals with more accurate tools to assess and mitigate this risk.

About SESAMm

Discover SESAMm provides AI-powered solutions to help investors and companies identify ESG controversies and risks before they escalate. Using state-of-the-art AI, SESAMm analyzes millions of sources in near real-time, detecting ESG controversies across public and private companies worldwide. Whether for due diligence, portfolio monitoring, or supplier risk management, SESAMm enables financial professionals to stay ahead of emerging risks and make more informed decisions.
Learn more at www.sesamm.com.

SESAMm’s AI Technology Reveals ESG Insights

Discover unparalleled insights into ESG controversies, risks, and opportunities across industries. Learn more about how SESAMm can help you analyze millions of private and public companies using AI-powered text analysis tools.