CFA Institute

What is machine learning in commodity futures?It is the application of supervised learning models to forecast returns in commodity futures markets. By grounding features in established theories such as the theory of storage and the hedging pressure hypothesis, ML identifies signals such as momentum, basis, carry, and skewness and translates them into long–short portfolio strategies. Why is ensemble modeling important in commodities?Ensemble modeling combines predictions from multiple horizons (short, medium, and long term) into a single signal. This approach reduces model risk, lowers volatility, and improves drawdown control compared with single-horizon models. Can machine learning generate alpha in commodity markets?Yes. When features are carefully designed and portfolios are constructed cross-sectionally, machine learning can uncover persistent patterns in commodity prices. These patterns align with macroeconomic cycles and provide systematic sources of alpha. Are the results interpretable for institutional investors?Yes. Because the features are drawn from established commodity economics, the models are not “black boxes.” They remain transparent, interpretable, and consistent with fiduciary and governance requirements. source

Allocations by institutional investors, represented by public pensions, have plateaued in recent years. This is unsurprising given the sheer volume of capital already committed, combined with the fact that private equity, the larger of the two allocations, has failed to deliver returns comparable to public markets for many years. The tapering of new institutional commitments, coupled with a clogged exit environment, created pressure across the private-markets ecosystem. Asset managers still had large portfolios to finance, consultants still had asset classes to recommend, and distributors still needed new products to sell. The solution was a structural innovation that allowed the industry to expand its investor base: semi-liquid vehicles designed specifically for individual investors and marketed as the “democratization” of private markets. These structures typically offer periodic liquidity, often through quarterly redemption windows, while investing in assets that may take years to sell at reliable prices. The appeal is obvious. Investors are offered exposure to private markets together with the appearance of stability and the reassurance that they can redeem capital periodically. The problem is that this model violates the previously explained principle of finance. Long-duration, difficult-to-price assets should never be financed with short-term liabilities unless a lender of last resort stands behind the structure. When that rule is ignored, the structure is unstable. As long as inflows continue and redemptions remain manageable, it seems advantageous to both investors and fund managers. But once investors begin to withdraw capital, the mismatch between liquidity promises and underlying assets becomes visible very quickly. History provides many examples of this dynamic. Wildcat banks in the 1800s, trust companies in the early 1900s, and investment bank warehousing facilities in the early 2000s. In each case, when confidence weakened, investors rationally attempted to redeem before others did. It doesn’t take long before investors run, simply in anticipation of other people running – which is the hallmark of a bank or fund run. This risk is substantially amplified when individual investors provide a large percentage of the capital. Taken together, semi-liquid private credit and private equity funds are unusually vulnerable to run mechanisms. Not only are Illiquid assets financed with redeemable capital, but the underlying investments were raised at the tail-end of two aged investment cycles. Financial history suggests that such combinations rarely remain stable for very long. They may function smoothly for several years. But when confidence weakens, the structural mismatch becomes impossible to ignore. That day arrived on February 18, when Blue Owl announced that it had permanently eliminated quarterly liquidity in its OBDC II private credit fund. source

To address these gaps, leading banks are adopting holistic AI risk and control approaches that treat AI as an enterprise-wide risk rather than a technical tool. Effective frameworks embed accountability, transparency, and resilience across the AI lifecycle and are typically built around five core pillars. 1. Board-Level Oversight of AI RiskAI oversight begins at the top. Boards and executive committees must have clear visibility into where AI is used in critical decisions, the associated financial, regulatory, and ethical risks, and the institution’s tolerance for model error or bias. Some banks have established AI or digital ethics committees to ensure alignment between strategic intent, risk appetite, and societal expectations. Board-level engagement ensures accountability, reduces ambiguity in decision rights, and signals to regulators that AI governance is treated as a core risk discipline. 2. Model Transparency and ValidationExplainability must be embedded in AI system design rather than retrofitted after deployment. Leading banks prefer interpretable models for high-impact decisions such as credit or lending limits and conduct independent validation, stress testing, and bias detection. They maintain “human-readable” model documentation to support audits, regulatory reviews, and internal oversight. Model validation teams now require cross-disciplinary expertise in data science, behavioral statistics, ethics, and finance to ensure decisions are accurate, fair, and defensible. For example, during the deployment of an AI-driven credit scoring system, a bank may establish a validation team comprising data scientists, risk managers, and legal advisors. The team continuously tests the model for bias against protected groups, validates output accuracy, and ensures that decision rules can be explained to regulators. 3. Data Governance as a Strategic ControlData is the lifeblood of AI, and robust oversight is essential. Banks must establish: Clear ownership of data sources, features, and transformations Continuous monitoring for data drift, bias, or quality degradation Strong privacy, consent, and cybersecurity safeguards Without disciplined data governance, even the most sophisticated AI models will eventually fail, undermining operational resilience and regulatory compliance. Consider the example of transaction monitoring AI for AML compliance. If input data contains errors, duplicates, or gaps, the system may fail to detect suspicious behavior. Conversely, overly sensitive data processing could generate a flood of false positives, overwhelming compliance teams and creating inefficiencies. 4. Human-in-the-Loop Decision Making Automation should not mean abdication of judgment. High-risk decisions—such as large credit approvals, fraud escalations, trading limits, or customer complaints—require human oversight, particularly for edge cases or anomalies. These instances help train employees to understand the strengths and limitations of AI systems and empower staff to override AI outputs with clear accountability. A recent survey of global banks found that firms with structured human-in-the-loop processes reduced model-related incidents by nearly 40% compared to fully automated systems. This hybrid model ensures efficiency without sacrificing control, transparency, or ethical decision-making. 5. Continuous Monitoring, Scenario Testing, and Stress SimulationsAI risk is dynamic, requiring proactive monitoring to identify emerging vulnerabilities before they escalate into crises. Leading banks use real-time dashboards to track AI performance and early-warning indicators, conduct scenario analyses for extreme but plausible events, including adversarial attacks or sudden market shocks, and continuously update controls, policies, and escalation protocols as models and data evolve. For instance, a bank running scenario tests may simulate a sudden drop in macroeconomic indicators, observing how its AI-driven credit portfolio responds. Any signs of systematic misclassification can be remediated before impacting customers or regulators. source

I have a sense that the investing community in Sweden is more female friendly than most other markets. Lips da Cruz observed, “Women are an important factor here in the Nordics. They are bringing a longer-term and more sustainable ‘feminine energy’ to the investment ecosystem.” There is a growing network of women-focused investing groups like RadCap Ventures and Feminvest, which aim to increase female participation in the investment arena. I have great admiration for KvinnoKapital, a local women’s networking group that helps women in asset management build contacts, exchange experiences, and inspire others to strengthen women’s position in the Nordic asset management industry. Does Stockholm’s dynamism, including its access to capital and entrepreneurial opportunities, also translate into more IPOs and greater opportunity for women? The people I interviewed were skeptical as there is no clear data to back up my theory; however, the general consensus is that Sweden’s investing culture, social norms, and supportive system likely help the overall quality and depth of the talent pool. Maria Lindbom, owner and CEO at Lager & Partners, opined: “From my perspective as a headhunter specialising in senior finance roles — and with my own background in finance — Stockholm’s success reflects a combination of structural factors, one of which is the strong representation of women in capital markets. I’ve seen how Sweden’s ecosystem consistently produces broad and deep talent pools.” Long-term thinking, strong governance, and high institutional trust are core features of the market, Lindbom noted. “The fact that many women progress into decision-making roles is a natural outcome of this environment, rather than a policy-driven exception.” So, while women’s representation is not the reason Stockholm is outperforming, it is very much part of a broader, well-functioning capital-market ecosystem that attracts long-term capital and supports sustainable growth. source

Something fundamental is happening in wealth management. It is not a trend and it cannot be captured with a few new buzzwords. It reflects a structural shift away from advisory models built primarily around products, performance reporting, and periodic engagement toward advice that is continuous, contextual, and directly connected to how clients actually live their lives. Women and next-generation investors sit at the center of this shift. They are inheriting assets at unprecedented scale, building wealth through entrepreneurship and equity compensation, and engaging with financial advisors earlier, and with clearer expectations than previous generations. They are not looking for a modernized version of traditional advice. They are looking for advice that feels relevant, transparent, and aligned with how they define value, risk, and success. That reality became clear during the research for Wealth Management with a Difference, a book I co-authored with Nick Rice. Across conversations with more than 80 industry leaders worldwide and a review of more than 100 global research reports, one theme emerged consistently: the demographic profile of wealth is changing faster than advisory models are evolving to meet it. For wealth managers, the implication is straightforward. Technical excellence remains foundational, but relevance now depends on how effectively that expertise is applied to real client decisions, starting with women and rising-generation investors. Women Investors: Redefining the Advisory Relationship Women are rapidly becoming one of the most influential forces in wealth management, not simply because they control more wealth, but because they are changing how wealth is evaluated and how advice is delivered. As women come to control a growing share of wealth — in the United States alone forecasts show women will control about $34 trillion in investable assets by 2030 — many are challenging long-standing assumptions about risk, return, and what meaningful advice looks like. “Many women think about portfolios differently, and they are not looking for a light touch,” Margaret Franklin, CFA, CEO of CFA Institute, told us during our research. “They want to understand how these things work on a deep level. They take a much more ‘total portfolio’ or ‘balanced scorecard’ approach — and that is really going to challenge advisors.” For many women investors, success extends beyond returns alone to include long-term security, resilience, family priorities, philanthropy, and legacy. What Wealth Managers Need to Know Women are not seeking simplification; they are seeking understanding. Traditional risk–return conversations must expand to include outcomes, trade-offs, and long-term impact. A “total portfolio” mindset requires integrating investments with planning, tax strategy, governance, and purpose. What Wealth Managers Need to Do Redesign discovery to surface priorities early. Move beyond standard fact-finding to explicitly explore how clients define security, independence, flexibility, and legacy, and document those priorities as planning constraints, not side notes. Reframe portfolio discussions around outcomes, not just allocations. Explain how investment choices support specific life objectives over time, including downside protection, liquidity, and optionality, not only expected returns. Make education a visible and continuous part of the relationship. Use scenario modeling, decision frameworks, and plain-language explanations to help clients understand why strategies are recommended and how they evolve as circumstances change. Treat women as primary decision-makers by default. Address women directly in meetings, ensure equal access to information and planning tools, and design strategies that reflect longevity, career interruption, and independence rather than assuming shared or secondary roles. Next-Generation Investors: Where Values and Wealth Intersect Next-generation investors, primarily Millennials and Gen Z, are reshaping the advisory landscape not only because of the scale of wealth moving into their hands, but because of how they choose to engage with it. Over the next two decades, more than $80 trillion is expected to transfer to younger individuals, bringing with it a different set of expectations about what portfolios should do and represent. Scale matters, but expectations matter more. For younger investors, portfolios are not just financial tools, they are expressions of intent. Rather than rejecting performance or discipline, these investors are expanding the decision framework itself. Advisors are increasingly expected to balance traditional measures of risk and return with more explicit conversations about values, trade-offs, and real-world outcomes, and to explain not just what they recommend, but how those decisions are reached. That expectation places new weight on communication. Expertise will always matter, but the industry has not consistently done a good job translating that expertise for clients. The ability to communicate differently — to meet clients where they are, explain complexity clearly, and invite dialogue — will be essential. In this environment, “soft skills” are no longer optional. They are central to effective advice. What Wealth Managers Need to Know Values-based investing is a baseline expectation, not a niche offering. Younger investors want transparency, context, and dialogue—not black-box solutions. Trust is built through engagement and explanation, not credentials alone. What Wealth Managers Need to Do Integrate values into portfolio construction without sacrificing rigor. Clearly articulate how impact, sustainability, or values-based preferences affect risk, return, diversification, and associated trade-offs. Make the decision process visible. Walk clients through how recommendations are formed, what alternatives were considered, and why certain paths were chosen, reinforcing confidence through transparency. Adapt communication to support ongoing dialogue. Replace one-way reporting with interactive conversations that invite questions, challenge assumptions, and evolve as clients’ priorities change. Build relationships before assets transfer. Engage next-generation clients early with planning relevant to their lives: career development, equity compensation, cash flow, and first liquidity events, rather than waiting for formal wealth transitions. How to Use Relevance as a Growth Strategy For many firms, marketing remains a lagging indicator of change. Even as women and next-generation investors reshape wealth management, much of the industry’s marketing still reflects an older advisory model, one centered on products, performance, and credentials rather than decisions, context, and trust. The firms gaining traction are not creating campaigns “for women” or “for next gen.” They are changing what their marketing signals about how advice actually works. Traditional wealth management marketing answers a question few clients are asking: What do you offer? Women and younger investors

For decades, the dominant explanation for low investment participation and suboptimal portfolio choices has been a lack of information. Investors, we are told, do not invest well because they do not understand risk, returns, or financial products. The implied solution is therefore to provide more education, clearer disclosures, and better data. Yet despite significant investments in financial literacy programs, improved transparency, and broader access to markets, many of the same behavioral patterns persist. Investors remain overly conservative in their asset allocation, exit markets during periods of volatility, delay participation despite rising income, and display deep mistrust of financial institutions. These outcomes are observed not only among retail investors, but also among highly educated and financially sophisticated individuals. The consequences are measurable: investors hold excess cash during expansions, sell into drawdowns, and systematically erode long-term returns. This begs the question for all investment professionals serving retail investors: What if information, while necessary, is not sufficient to change behavior? Why Information Isn’t Enough Traditional financial theory assumes that once individuals are properly informed, they will act in a manner consistent with rational optimization. In practice, however, investment decisions are rarely made in neutral or controlled environments. They are made under uncertainty, emotional stress, social influence, and time pressure. When markets decline sharply, investors do not calmly reassess expected returns and correlations; they experience fear. When volatility rises, risk is not processed as a statistical distribution but as a psychological threat. In such contexts, additional information often fails to improve decision-making and can, in some cases, aggravate anxiety and inaction. Empirical evidence from behavioral finance supports this observation. Individuals are loss averse, overweight recent experiences, discount future outcomes, and rely on heuristics when faced with complexity. These tendencies persist even among financially literate investors. Firms that ignore this reality will continue to attribute client outcomes to behavior rather than to the systems that shape it. Behavior Follows Design One of the most robust insights from behavioral research is that behavior responds strongly to context. Defaults, framing, choice architecture, and institutional signals all influence decisions often more powerfully than information itself. For example, participation rates in retirement plans vary dramatically depending on whether enrollment is opt-in or opt-out, even when contribution options and disclosures are identical. Similarly, investors’ willingness to hold risky assets is affected by how performance information is presented, the frequency of feedback, and the perceived behavior of peers. These findings suggest that investment outcomes are shaped not only by what investors know, but by how investment systems are designed. Decisions are embedded in environments that either amplify or dampen behavioral biases. Despite this, many financial systems continue to assume high levels of self-control, foresight, and emotional resilience from participants. Products are designed with an implicit expectation of discipline. Advice frameworks assume follow-through. Regulation often assumes compliance once rules are clearly communicated. When outcomes fall short, the response is frequently to intensify education efforts rather than to reconsider the underlying design assumptions. From Education to Design Recognizing the limits of information does not diminish the role of investment professionals. It reframes it. The question shifts from “How much more can we explain?” to “How well are decisions being designed?” This reframing has important implications across the investment ecosystem: For asset managers, product success should not be evaluated solely on performance metrics. The behavioral journey of the investor such as how they enter, stay invested, and react to volatility is equally important. Products that are theoretically optimal but behaviorally fragile are unlikely to deliver intended outcomes at scale. For financial advisors, effectiveness depends not only on the quality of recommendations, but on when and how advice is delivered. Timing, framing, and emotional context shape whether advice is acted upon, particularly during periods of market stress. For policymakers and regulators, participation, trust, and inclusion are not primarily communication challenges. They are institutional design challenges. Rules and safeguards influence behavior not only through enforcement, but through the signals they send about trust, stability, and fairness. Designing for Real Investors A design-oriented approach to investment behavior does not reject rationality; it recognizes its limits. It acknowledges that humans operate with bounded rationality and predictable biases, and that systems should be built accordingly. This means asking different questions: Where can defaults support long-term behavior rather than short-term impulses? How can choice sets be simplified without reducing meaningful options? What forms of friction are helpful, and which are harmful? How do institutional rules affect trust and perceived legitimacy, especially in emerging markets? How do we reframe financial education as support, not a solution? These are not theoretical concerns. They are practical design questions with direct implications for asset allocation, market participation, and financial stability. Conclusion The persistent gap between investment knowledge and investment behavior suggests that the problem is not simply one of education. Information matters, but it operates within environments that shape decisions. If investment outcomes consistently fall short of intent, the critical question is not why investors fail to act rationally. It is whether the products, advice frameworks, and institutional rules they encounter are designed for real human behavior. Improving investment outcomes, therefore, requires a shift in focus from explaining more to designing better. From assuming rational agents to working with predictable behavior. From treating behavior as noise to recognizing it as a central feature of financial decision-making. This shift is not optional. It is increasingly essential for investment professionals seeking durable outcomes in an uncertain world. source

The CBOE Volatility Index (VIX) came on the scene in the 1990s as a way for investors to track expected risk in the market going forward. The Chicago Board Options Exchange’s VIX does something unique in that it uses 30-day options on the S&P 500 Index to gage traders’ expectations for volatility. In essence, it gives us a forward estimate of what the market thinks volatility in equities is going to be. But how accurate is this measure on a realized basis and when does it diverge from the market? We tackled this question by comparing the full spectrum of VIX data going back to 1990 to the realized volatility of the S&P 500 Index. We found that, on average, the market overestimated volatility by about 4 percentage points. But there were unique times when there were significant misestimations by the market. We tell this story in a series of exhibits. Exhibit 1 is an image of the full time series of data. It shows that, on average, the VIX overshot realized volatility consistently over time. And the spread was consistent as well, except for during spike periods (times when markets go haywire). Exhibit 1. In Exhibit 2, we summarize the data. The average S&P 500 Index realized volatility on a 30-day forward basis was 15.50% over the 35-year period. The average VIX (30-day forward estimate) was 19.59% over the same period. There is a 4.09% spread between the two measures. This implies that there is an insurance premium of 4.09 percentage points on expected volatility to be insulated from it, on average. Exhibit 2. Average (%) Median (%) S&P Volatility (forward 30 days) 15.50427047 13.12150282 VIX (30-day Estimate) 19.59102883 17.77 Difference (Actual Vs Estimate) -4.086758363 -4.648497179 Next, we turn toward a time when no major crisis happened: from 1990 to 1996. Exhibit 3 highlights how markets worked during these normal times. The VIX consistently overshot realized volatility by approximately five to seven percentage points. Exhibit 3. Exhibit 4 depicts a very different period: the 2008 global financial crisis (GFC), and we can see a very different story. In July 2008, realized volatility on a 30-day, forward-looking basis began to spike over the VIX. This continued until November 2008 when the VIX finally caught up and matched realized volatility. But then realized volatility fell back down and the VIX continued to climb, overshooting realized volatility in early 2009. Exhibit 4. This appears to be a standard pattern in panics. VIX is slow to react to the oncoming volatility and then overreacts once it realizes the volatility that is coming. This also says something about our markets: The Federal Reserve and other entities step in to quell the VIX once things look too risky going forward, thereby reducing realized volatility. In Exhibit 5, we saw this dynamic again during the COVID period. Exhibit 5. The Exhibits yield two interesting takeaways. One, investors, on average, are paying a 4% premium to be protected from volatility (i.e. the difference between the VIX and realized volatility). Two, the market is consistent in this premium; is slow to initially react to large, unexpected events like the GFC and COVID; and then overreacts. For those that are using VIX futures or other derivatives to protect against catastrophic events, these results highlight how much of a premium you can expect to pay for tail risk insurance as well as the risk you take in overpaying during times of market panic. If you liked this post, don’t forget to subscribe to the Enterprising Investor. All posts are the opinion of the author. As such, they should not be construed as investment advice, nor do the opinions expressed necessarily reflect the views of CFA Institute or the author’s employer. Image credit: ©Getty Images / Ascent / PKS Media Inc. Professional Learning for CFA Institute Members CFA Institute members are empowered to self-determine and self-report professional learning (PL) credits earned, including content on Enterprising Investor. Members can record credits easily using their online PL tracker. source