Flirting with Models

In this episode I speak with Faheem Osman, Managing Director and Global Head of QIS Structuring at Macquarie Group. Faheem has spent nearly two decades inside major investment banks — first at Citi, where he spent about ten years on the commodities trading and structuring side, and now at Macquarie, where he's built out their cross-asset QIS business. Commodities, though, remain firmly in the DNA of what Macquarie does, and it's where Faheem cuts his teeth. We spend the bulk of our conversation exploring commodity QIS as a distinct and, in Faheem's view, underappreciated source of systematic returns. Faheem walks us through strategies like curve carry and index congestion, explains why commodities have historically delivered some of the highest risk-adjusted returns of any asset class in QIS, and makes the case for why these premiums haven't simply been arbitraged away. We also dig into commodity volatility selling, the shift toward weekly options, and close with a timely discussion on what the explosion of 0DTE options means for the vol risk premium more broadly. Please enjoy my conversation with Faheem Osman.

Today, I’m speaking with Richard Craib, the CEO and founder of Numerai. If you’ve heard of Numerai before and thought of it as an interesting experiment at the intersection of data science and crypto, it’s worth updating that mental model. Over the last few years, Numerai has quietly grown from roughly $60 million in assets to over $600 million. JPMorgan has invested and secured $500 million of capacity, and Numerai recently raised a Series C at a $500 million valuation led by top university endowments. This is no longer a toy project. It is a real, institutional-scale market-neutral hedge fund with a very unconventional engine. In this conversation, we go deep into how Numerai actually works. Richard walks through the core insight behind Numerai’s design: that crowd-sourced alpha only works if incentives are aligned, not just participation. Simply opening up data and ranking models creates incentives to game the system, not to produce durable signals. That realization led to the introduction of the Numeraire token. By forcing researchers to stake real capital behind their predictions, Numerai shifts from a leaderboard-driven experiment to a capital-weighted signal engine. Instead of rewarding activity, the system rewards conviction, accountability, and uniqueness, creating a self-filtering model that naturally reduces noise and discourages the behaviors that caused earlier crowd-sourced platforms to fail. We also talk about portfolio construction and risk management, including how Numerai neutralizes common factor exposures, what went wrong during the 2023 drawdown, and how those lessons reshaped their approach to diversification and concentration. Finally, we look forward, covering the limits of crowd-sourced modeling, the next frontier for Numerai’s research ecosystem, and how Richard sees AI agents reshaping model development. Please enjoy my conversation with Richard Craib.

Today, I’m speaking with Ruslan Fakhrutdinov, the founder of Extended, a decentralized perpetual futures exchange. Ruslan is the fifth perpetual futures exchange founder I’ve had on the podcast, and that’s very intentional. Flow continues to move toward these platforms, and while trading perps can feel familiar to anyone coming from centralized or traditional exchanges, the way risk is absorbed and resolved under the hood for decentralized exchanges can be very different. In this episode, we go deep on the design of perp DEX vaults and the role they play as a liquidity and risk backstop for the entire exchange. Ruslan walks through how platforms choose between protecting system solvency, safeguarding vault depositor capital, and managing trader losses, particularly during stress events. We also discuss how settlement finality, governance intervention, and liquidation design determine where losses ultimately land. We spend time on Extended’s introduction of vault shares as collateral, why that design can be powerful, and the new risks it introduces if boundaries aren’t explicit. Ruslan lays out the risk-management waterfall: when the vault steps in as a counterparty, when it refuses additional exposure, and when traders are pushed into forced deleveraging or auto-deleveraging instead. We close by connecting this framework to Extended’s next phase, expanding cross-asset margin, and what it takes to design a system that still behaves predictably when markets break. Please enjoy my conversation with Ruslan Fakhrutdinov.

Today, I am speaking with Angana Jacob, Head of the Research Data group within the Enterprise Data business at Bloomberg. We talk about Angana’s career path through quantitative research and data platforms, and how the industry has evolved from a world dominated by bespoke models and backtests to one where many models have become increasingly commoditized. A central theme of our conversation is the idea that while models are easier than ever to replicate, data — how it’s sourced, cleaned, standardized, linked, and delivered — has become the true competitive moat. We discuss what it means to “do data correctly,” how Bloomberg decides which datasets to build or sunset, how modern quants think about their data pipelines and tech stacks, and why aligning research data with production and back-office systems matters more than most people realize. Throughout the episode, we focus on Bloomberg’s goal of shortening a client’s time to alpha, and what that looks like in practice. At its core, this episode is about a simple but powerful idea: when everyone has access to similar models, durable edge increasingly comes from the data beneath them. Please enjoy my episode with Angana Jacob.

A few years ago, I sat down with Moritz Seibert and Moritz Heiden of Takahe Capital to talk about trend following at the edges of the futures markets: places where liquidity is thin, contracts are obscure, and capacity constraint is a feature, not a bug. Since then, despite strong performance, asset growth, and even winning industry awards, they made a very un-industry decision: they shut down their original fund. In its place, they launched a new Global Markets Fund built to stay small, so they can trade calendar and product spreads, niche agricultural markets, and other idiosyncratic contracts at equal risk to more standard markets. In this conversation, we unpack that decision, explore how you systematize trend on markets where liquidity does not exist on screen, and go deep on why spreads represent a fundamentally different opportunity set than outright futures. We also talk about what’s next: from prediction and event markets to new ways of thinking about macro trends and alternative data. I hope you enjoy my conversation with Moritz Seibert and Moritz Heiden.

In this episode I speak with Annanay Kapila, founder and CEO of QFEX, a 24/7 centralized perpetual-futures exchange for traditional financial markets. Before founding QFEX, Annanay worked at Flow Traders and Tower Research, where he was introduced to high frequency trading and market microstructure in both crypto and traditional markets. Insights gleaned during these experiences lead him to the conclusion that the perpetual futures model applied to traditional, so-called “real world asset” markets, like equities, was an inevitable future and one he wanted to build. In this episode, we discuss the ramifications of what that world looks like. First, we discuss what perpetual futures are and their distinguishing characteristics from traditional futures. Then we discuss how perpetual futures can work in markets – like single-name equities – where the underlying do not trade 24/7, and have unique features like corporate actions, opening and closing price auctions, and limit-up/limit-down bounds. A consistent thread throughout the entire conversation is risk management. When leverage is your key feature, it is important to think long and hard about how and when liquidations might occur and the safest way to process them. Finally, we discuss why Annanay believes why perpetual futures will succeed where spot tokenization failed and his view on the current regulatory landscape. Please enjoy my conversation with Annanay Kapila.

In this episode, I speak with Jay Rajamony, Director of Alternatives at Man Numeric. Jay has been with the firm since 2004, giving him a front-row seat to the evolution of quant equity: from simple factor models and broad signals to today’s world of alternative data, model ensembles, and human-machine collaboration. We start with the history: what’s changed in quant over the last two decades, why the 2007 quant quake still matters, and how the definition of “alpha” has shifted alongside new tools and data. From there, we explore the interplay between factors and macro regimes, how sparse datasets are reshaping the research process, and what it means to manage risk in a world where your models don’t always line up with reality. Jay also offers a compelling perspective on how modern quant investing isn’t just about signal breadth anymore—it’s about firm breadth, organizational design, and knowing when to lean in and override the machine. Please enjoy my conversation with Jay Rajamony.

In this episode I’m joined by Vladimir Novakovski, founder and CEO of Lighter, a decentralized crypto exchange. To kick off the conversation, we explore Lighter's three big design choices: it’s built as a custom Layer-2 on Ethereum, it relies on zero-knowledge circuits for proving transactions, and it runs with a private sequencer. Don't worry – if that sounds like gibberish, Vlad explains it all. Each of those decisions comes with trade-offs — but also big potential advantages. We discuss why Ethereum remains the natural home for new rollups, from inheriting its security to tapping into DeFi’s growing composability. We also break down what zk circuits actually are, why they matter for trust and security in a derivatives exchange, and how they’re verified in practice. From there, we tackle the business side: how you bootstrap liquidity in a brand-new DEX, why Lighter went with an unusual fee model and the key lessons learned during an extended private beta. Finally, we zoom out to the bigger picture. What might DeFi look like if composability really takes hold? Could specialized rollups like Lighter become the backbone of an on-chain financial system, rather than just another venue for speculation? Please enjoy my conversation with Vlad Novakovski.

In this episode, I speak with Antti Ilmanen, Principal and Global Co-head of the Portfolio Solutions Group at AQR Capital Management. Antti has long been one of the most thoughtful voices in the world of expected returns, having written not one, but two landmark books on the subject. But in his latest paper series, he returns to the topic with fresh urgency—probing the difference between objective and subjective expectations, and asking why even rational models can go so wrong in real time. We explore everything from CAPE ratios and market timing accusations, to why equity investors tend to extrapolate while bond investors expect mean reversion. We dig into how behavioral biases, valuation anchors, and structural shifts collide when forming capital market assumptions—and how Antti and the AQR team try to navigate that mess themselves. If you’re in the business of long-term forecasting or just curious why markets often act like they’ve never read the textbooks, this is a conversation you won’t want to miss. Please enjoy my conversation with Antti Ilmanen.

In this episode, I speak with Chris Carrano, Vice President of Strategic Research at Venn by Two Sigma. Chris has had a rare vantage point in the world of factors — spanning smart beta, long/short hedge funds, and risk modeling — and that experience has shaped a thoughtful view of what factors really are and how they can be practically used. We dive into the philosophy and design behind Venn: why it uses just 18 orthogonalized factors, how it blends Lasso and OLS to reduce overfitting, and why it prioritizes interpretability over complexity. We also tackle messy real-world challenges: how to analyze private markets with sparse data, how to trust synthetic return streams, and where to draw the line when using monthly snapshots that embed structural portfolio shifts. Finally, we explore what it means to make factor results actionable—whether through stress testing, residual interpretation, or portfolio diagnostics. Please enjoy my conversation with Chris Carrano.

In this episode I speak with Jeffrey Rosenburg, Managing Director at BlackRock where he leads active and factor investments for mutual funds, ETFs, and institutional portfolios for the Systematic Fixed Income team. In the first half of the conversation we discuss the history of quant fixed income. Specifically, its evolution within the halls of sell-side institutions and how solutions were shaped by demand for underwriting, securitization, and derivatives. We then make the leap to the buyside, where Jeff outlines the topology of systematic fixed income solutions at BlackRock. We quickly dive into the details, discussing topics such as: why factor investing exists predominately in the credit space, why characteristic specificity within the fixed income space is so important, why quant fixed income needs more PMs but fewer researchers than quant equity, how ETFs changed the liquidity landscape, and whether the equity pod-shop model is possible for fixed income. What ultimately becomes clear, through both explanation and example, is that while the terms and ideas of systematic fixed income will be familiar to those in the quant equity space, the Devil lies deeply in the details of implementation. I hope you enjoy my conversation with Jeff Rosenburg.

In this episode I speak with Edward Yu, co-founder of Variational. We begin the conversation with Edward’s background in crypto OTC markets. He explains how the space evolved away from Telegram chats, the complexities of pricing derivative structures on the long-tail of alternative crypto currencies, and the sources of natural flow in the space. This experience led Edward to co-found Variational, which seeks to bring the trillion dollar OTC derivatives market on-chain by disaggregating settlement, margining, and derivative payoff logic into programmable primitives. Built on top of Variational is the OMNI perp dex – or decentralized perpetual futures exchange for the non-crypto-speaking listeners. Unlike other perp dexes that are build around a centralized order book, OMNI effectively acts as a user interface to a OTC RFQ system. On the other side is OLP – the OMNI Liquidity Provider. This structure allows OMNI to provide significant depth of liquidity on a huge breadth of investable assets despite the platform being in closed beta at the time of recording. Given its unique design, we spend a significant amount of time discussing the pros, cons, and risks of this structure. This conversation is, obviously, out of my usual realm. But for those listeners interested in market structure and where the world of finance may be headed, this is one not to miss. Please enjoy my conversation with Edward Yu.

My guest this episode is Benjamin Hoff, Global Head of Commodity Strategy and Research at Société Générale. Ben started his career in rates before making the jump to commodities, and that lens—shaped by curve arbitrage, convexity, and carry—colors everything he does. In this conversation, we explore how commodities differ fundamentally from other asset classes: the importance of cash-and-carry economics, the sparse information cadence that rewards technical models, and the physical realities that challenge purely quantitative approaches. We also dive into Ben’s more recent work on the geometry of the futures surface, how convexity and skewness may be misunderstood, and why tools like Lévy area might help uncover non-linear structure in the data. Whether you’re deep in the weeds of term structure trading or just curious about how to systematize chaos in barrels and bushels, this is a conversation you won’t want to miss.

My guests today are Roxton McNeal, Managing Director and Head PM of QIS Investments and Siddharth Sethi, portfolio manager and Head of QIS structuring. Together, they’re spearheading the development of QIS-driven solutions at Simplify. In this conversation, we explore what it takes to build and manage a multi-strategy QIS portfolio—from infrastructure requirements to portfolio construction and risk management. We discuss: • The structural vs. academic premia distinction and why it matters. • How Simplify evaluates and customizes QIS offerings from banks. • The need and challenges of dynamic allocation across dozens of strategies. • How QIS strategies integrate with traditional beta portfolios. • The operational and counterparty considerations of trading these strategies. For those interested in the practical realities of QIS investing, this episode provides a deep dive into both the opportunities and challenges of running a systematic, multi-strategy portfolio. I hope you enjoy my conversation with Roxton McNeal and Siddharth Sethi.

Scott Phillips is just the second independent trader I’ve interviewed for this show. Like many independent traders, Scott found that his constraints – including the size of their capital pool, the ability to execute trades efficiently, and a lack of supporting infrastructure – made trading anything but loose-pants trend following almost impossible in traditional markets. These constraints led Scott to look for easier markets to trade: markets where the edges were so big they could survive inefficient implementations. All of which brought Scott to crypto in the late 2010s. While our conversation is, at a high level, mostly about trend following, we spend a lot of time discussing what makes trading these markets unique. For example, with tens of thousands of spot cryptocurrencies, how do you choose what to trade? How do you choose which venues to trade at when liquidity is so fragmented? How do you deal with the fact that both crime and degenerate gambling are real idiosyncratic factors? More than anything, painted between the lines, Scott provides a master class in thinking about edges. I hope you enjoy my conversation with Scott Phillips.

Today I’m talking to Thao Tran, Co-founding Partner at Vamient Capital. This episode was born from a question I had watching the NFT market place: how do you make markets in illiquid, non-fungible assets? Clearly people were doing it and I wanted to know how it differed from traditional market making. Several people recommended I speak with Thao, and she was kind enough to oblige, despite NFT market making being just a small component of what she does. In this conversation, we walks me through how the NFT market place has evolved, how she thinks about managing inventory risk, key features that impact spreads, and how platform evolutions changed orderbook strategies. In the back half of the conversation, Thao shares her thoughts on the state of crypto markets today, the emerging opportunities in decentralized exchanges, and how the landscape of alpha opportunities has changed over the last two years. I hope you enjoy my conversation with Thao Tran.

My guest today is Victor Haghani, founder of Elm Wealth. Victor is, in many ways, one of the last tactical asset allocators standing after the 2010s. That might be because Victor wouldn’t categorize himself as such. Rather, he sees his dynamic index investing approach not as a tactical alternative to traditional static portfolios, but as the rational approach for anyone starting from first principles. This conversation dances between theory and implementation. Victor is just as comfortable sharing his thoughts on where equity market risk comes from as he is defending payout-adjusted CAPE as a metric for forecasting long-run returns. If you’re passionate about asset allocation, you’ll find lots to think about in this one. Please enjoy my conversation with Victor Haghani.

In this episode of the Get Stacked Investment Podcast, Corey and Rodrigo have an insightful conversation with Jonathan Glidden, Chief Investment Officer of the Delta Airlines Pension Plan. Since joining in 2011, Jonathan has been pivotal in elevating Delta’s pension plan funded status from 38% to over 100%. They delve into Jonathan's unconventional career journey, his implementation of portable alpha strategies, and share valuable lessons learned from turbulent financial periods such as 2008 and 2020. Whether you're a seasoned investor or new to the concept of portable alpha, this episode provides a masterclass on optimizing pension plan management through innovative investment strategies.

In this episode, I speak with Farouk Jivraj, Portfolio Manager and Head of Alternative Risk Premia at Fidelity Investments’ Asset Management Solutions division. After spending nearly a decade on the sell side, Farouk joined Fidelity in 2021 with the goal of building out an alternative risk premium platform, tapping into the best of what both the sell-side QIS desks have to offer and what can be built in-house. We spend the majority of the conversation peeling apart the layers of Farouk’s 5-step process for implementing alternative risk premia strategies. He shares his thoughts on how to classify different premia, why thoughtfully-constructed peer groups are an important evaluation tool, how to go about selecting specific strategies, how to construct portfolios of alternative risk premia, and the actual rubber-meets-road implementation practicalities. Please enjoy my conversation with Farouk Jivraj.

In this episode I chat with Giuseppe Paleologo – or Gappy as he likes to be called. Currently on garden leave, Gappy has previously worked in Risk & Quantitative Analytics at Citadel, as Head of Enterprise Risk at Millennium, and most recently as Head of Risk Management at HRT. We begin the conversation with a discussion as to what a quant researcher actually does at a multi-manager hedge fund. As a semi-support role to the fundamental PMs, Gappy explains how portfolio manager coverage, factor hedging, and internal alpha capture can all work together to help maximize firm P&L. We then discuss the broad field of factor research and portfolio construction, where Gappy shares some of his strongly held views, both on how factors should be constructed as well as how they should be utilized. Topics include returns versus characteristics, mixing versus integrating alpha signals, single- versus multi-period optimization, and linear- versus non-linear models. Please enjoy my conversation with Giuseppe Paleologo.