The Blushing Quants Podcast

Eyal Neuman is a mathematical finance researcher and co-director of the quantitative finance master’s program at Imperial College London. His work spans probability, stochastic control, market microstructure, price impact, optimal execution, multi-agent systems, and quantum computing in finance.

Eyal’s path began with industrial engineering at Tel Aviv University before his interest shifted toward mathematics and probability. He completed graduate research at the Technion, followed by postdoctoral work in Hong Kong and Rochester, New York. At Imperial College, he began combining theoretical research with practical financial problems through collaborations with academics, practitioners, and Capital Fund Management.

In this episode, Eyal joins us for an in-depth conversation about connecting academic mathematics with real financial markets, constructing useful models from complex trading problems, understanding market impact, and identifying where emerging technologies may offer genuine value.

Eyal explains why meaningful quantitative research often develops at the intersection of mathematical depth and practical relevance. Industry practitioners understand the problems they face but may lack the time to build rigorous models, while academic researchers can provide mathematical structure, analytical tools, and a deeper examination of the underlying trade-offs.

We discuss how complex market behavior can be translated into a tractable model. Eyal explains why researchers must identify the most important state variables without attempting to reproduce every detail of reality. Models that are too simple may miss the essential mechanism, while models that are too complicated can become impossible to solve, difficult to interpret, and vulnerable to overfitting.

The conversation explores stochastic control and its applications to portfolio construction, market making, and optimal execution. Eyal explains how researchers define an objective, model the evolution of relevant state variables, and derive a strategy that balances expected performance, trading costs, market impact, and risk.

We then examine price impact and the problem of executing large positions. Eyal discusses propagator models, statistical estimation, liquidity, execution horizons, and how previous trades can influence future price movements. We explore how an investor can divide a large order over time to reduce costs while still completing the required transaction.

The discussion goes deeper into multi-agent markets and signal crowding. When many participants trade using the same information, their collective order flow can reinforce the signal, increase market impact, and reduce the profitability available to each trader. Eyal explains how mathematical models can make these relationships more transparent and help quantify interactions that practitioners already recognize intuitively.

We also explore passive execution through limit orders. Instead of modeling every individual market participant, researchers can study the market’s average response to an order at a particular distance from the best bid or ask. This creates a more tractable framework for deciding how much liquidity to provide, where to place orders, and how to manage inventory and execution risk.

Eyal discusses the contribution of econophysics and empirical market laws, including the square-root relationship between traded quantity and price impact. We examine the difference between observing a statistical regularity and constructing a model that explains how the behavior of traders may generate it.

The conversation also covers quantitative finance education at Imperial College. Eyal explains how the program combines foundational subjects such as stochastic processes, derivatives pricing, and interest-rate models with newer areas including machine learning, deep learning, market microstructure, and quantum computing. Practitioner lectures, industry advisors, internships, and applied research help connect academic training with the skills required in professional quantitative roles.

Finally, we discuss the current state of quantum computing in finance. Eyal explains why practical use cases remain limited and uncertain, while highlighting potential applications in derivatives pricing, high-dimensional partial differential equations, optimization, and sampling rare distributions for risk scenarios.

A technical and thoughtful conversation on mathematical finance, industry collaboration, stochastic control, market impact, optimal execution, signal crowding, quantitative education, and the developing role of quantum computing in financial markets.

 

*DISCLAIMER*

The information shared on this podcast is for educational and informational purposes only and reflects the personal opinions of the hosts and guests at the time of recording. Nothing in this podcast constitutes financial, investment, legal, tax, or trading advice, and nothing should be interpreted as a recommendation to buy, sell, or hold any security, cryptocurrency, derivative, or financial product.

Trading and investing involve substantial risk, including the possible loss of all or part of your capital. You are solely responsible for your own decisions, and you should consult a qualified professional before making financial decisions. By listening to this podcast, you agree that the hosts, guests, and producers are not liable for any losses or damages arising from the use of any information discussed.

Joseph Chen is a quantitative finance professional with extensive experience building trading systems, backtesting frameworks, and research infrastructure for multiple financial firms.

In this episode, Joseph joins us for a technical and practical conversation about designing institutional-grade quantitative research systems, integrating artificial intelligence into established workflows, validating financial data, and moving systematic strategies from backtesting into live trading.

Joseph explains why asking an AI coding tool to build an entire trading system from scratch can lead to missing components, inconsistent assumptions, and unreliable results. Instead, he argues that AI should operate within a modular framework containing trusted data sources, reusable libraries, clearly defined interfaces, and established backtesting procedures.

We discuss the importance of data integrity and why information from even reputable vendors must still be inspected carefully. Joseph explains how corporate-action adjustments, raw versus adjusted prices, missing observations, timestamps, exchanges, currencies, and instrument specifications can materially change the outcome of a backtest.

The conversation explores the architecture of an event-driven trading system. Joseph breaks down the roles of data loaders, bar engines, strategy modules, portfolio components, order-management systems, matching engines, reporting tools, and monitoring modules. He also explains why intermediate calculations, signals, and order events should be recorded so the entire research process can be audited and reproduced.

Joseph discusses the challenge of supporting multiple asset classes and trading frequencies within one framework. Equities, futures, foreign exchange, fixed income, and options each have different conventions, data requirements, execution rules, and risk characteristics. Similarly, infrastructure designed for daily or minute-level strategies may be unsuitable for high-frequency trading, where order-book data and millisecond-level performance become critical.

We examine the transition from backtesting to simulation and live trading. Joseph explains why the same strategy logic should remain consistent across all three environments, with only the order destination and execution mechanism changing. A realistic simulation engine should reproduce broker callbacks, partial fills, matching rules, transaction costs, and market-specific execution behavior as closely as possible.

The discussion also covers the risks of using AI to optimize strategies repeatedly on the same historical data. Faster experimentation can easily accelerate overfitting, making human supervision essential. Joseph emphasizes that researchers must evaluate whether each modification is economically reasonable instead of allowing AI to search blindly for the highest historical return.

We also explore machine learning in quantitative finance, including the trade-off between predictive power and interpretability. Joseph explains why smaller datasets may be better suited to simpler tree-based models, while deep neural networks or transformers may be appropriate only when researchers have enough data and a strategy that genuinely requires that level of complexity.

Finally, Joseph outlines how he evaluates a new systematic strategy. The process begins by confirming that the existing infrastructure can support the idea, followed by controlled backtesting, parameter-sensitivity analysis, realistic simulation, and deployment with limited capital. Exposure should increase only when live behavior remains consistent with the original research.

A detailed conversation on backtesting architecture, systematic research, AI-assisted development, data integrity, execution simulation, machine learning, strategy validation, and the infrastructure required to transform a quantitative idea into a live trading system.

*DISCLAIMER*

The information shared on this podcast is for educational and informational purposes only and reflects the personal opinions of the hosts and guests at the time of recording. Nothing in this podcast constitutes financial, investment, legal, tax, or trading advice, and nothing should be interpreted as a recommendation to buy, sell, or hold any security, cryptocurrency, derivative, or financial product.

Trading and investing involve substantial risk, including the possible loss of all or part of your capital. You are solely responsible for your own decisions, and you should consult a qualified professional before making financial decisions. By listening to this podcast, you agree that the hosts, guests, and producers are not liable for any losses or damages arising from the use of any information discussed.

Peter Kostovčík is a quantitative trader and researcher with a background in mathematics, machine learning, systematic equities trading, and the development of live trading systems.

In this episode, Peter joins us for a practical conversation about machine learning in finance, feature engineering, research pipelines, trading-system design, portfolio construction, position sizing, liquidity, and the growing role of AI agents in quantitative research.

Peter explains why the model itself is often the least important part of a machine-learning strategy. While researchers may focus on increasingly sophisticated algorithms, he argues that most of the real work lies in understanding the data, developing meaningful features, defining the correct objective, and forming ideas that reflect how markets actually operate.

We discuss when machine learning is useful and when it may introduce unnecessary complexity. Peter explains why it can be effective when ranking or classifying thousands of equities, but far more vulnerable to overfitting when applied to a single asset with only one historical time series.

The conversation explores how Peter uses classification, probability distributions, clustering, and other machine-learning methods to narrow large investment universes into manageable groups of potential trades. Rather than expecting a model to predict an exact return, he focuses on identifying relative opportunities that can be combined within a portfolio.

Peter also breaks down his research process, beginning with an idea and a simple statistical test before moving into feature engineering or model development. We discuss in-sample analysis, out-of-sample validation, protected backtest periods, and why repeatedly examining test results can quietly transform supposedly unseen data into another source of overfitting.

The discussion then moves from research into live implementation. Peter explains why liquidity, spreads, slippage, short-selling restrictions, turnover, market capacity, and execution constraints must be considered from the beginning. A strategy may look attractive statistically while remaining impossible to trade at meaningful size.

We also examine the role of AI agents in quantitative research and software development. Peter shares how AI has accelerated his ability to build research infrastructure and test ideas, while emphasizing that it still requires experienced supervision. Without clear constraints and market knowledge, an AI-generated system may reproduce unrealistic assumptions found in academic papers, online examples, and historical training data.

Peter discusses his preference for equities, where large and diverse universes provide more opportunities for systematic research. He also shares lessons from expanding strategies into international markets, where a valid signal can still fail because the available liquidity is insufficient.

Finally, we explore portfolio construction and position sizing. Peter explains why he begins with equal weighting before adding sector, liquidity, volatility, and concentration constraints. We compare equal weighting with probability-based sizing, discuss the limitations of universal formulas such as the Kelly criterion, and examine why the appropriate solution depends on the specific strategy, holding period, and market environment.

A practical and detailed conversation on machine learning, feature engineering, systematic trading, research validation, AI agents, liquidity, portfolio construction, and the challenges of turning a promising model into a robust live trading system.

 

*DISCLAIMER*

The information shared on this podcast is for educational and informational purposes only and reflects the personal opinions of the hosts and guests at the time of recording. Nothing in this podcast constitutes financial, investment, legal, tax, or trading advice, and nothing should be interpreted as a recommendation to buy, sell, or hold any security, cryptocurrency, derivative, or financial product.

Trading and investing involve substantial risk, including the possible loss of all or part of your capital. You are solely responsible for your own decisions, and you should consult a qualified professional before making financial decisions. By listening to this podcast, you agree that the hosts, guests, and producers are not liable for any losses or damages arising from the use of any information discussed.

Julien Riposo is the Head of Quantitative Research at Stewardship and Governance Associates and the founder and CEO of JR Enterprise. With a PhD in Applied Mathematics and a background spanning quantitative finance, model validation, blockchain, digital assets, and market infrastructure, Julien focuses on transforming abstract mathematical ideas into practical decision-making systems.

In this episode, Julien joins us for an in-depth conversation about mathematical abstraction, complex financial systems, model robustness, asset valuation, artificial intelligence, and the process of turning research into tools that can support real decisions.

Julien explains the difference between a model that appears convincing and one that can be trusted in practice. We discuss assumptions, calibration, sensitivity analysis, stress testing, implementation constraints, and why researchers must clearly define the conditions under which a model remains reliable.

The conversation explores two dimensions of model reliability: stability through time and structural robustness at a particular moment. Julien explains why a successful backtest is not enough and how mathematics, probability, stochastic processes, and network models can help researchers understand how systems behave under uncertainty.

We also discuss the role of abstraction in quantitative research. Straightforward problems may be addressed through established optimization methods, but more complex questions often require researchers to step outside familiar frameworks, rethink the structure of the problem, and draw ideas from other disciplines.

Julien shares examples from blockchain, governance systems, biology, and finance to show how graph theory, diffusion models, and related mathematical structures can describe interactions between connected agents. He explains how similar mathematical languages may appear across very different domains, even when their practical interpretations remain distinct.

The discussion then moves to system design and the importance of properly defining a problem before selecting a model or pursuing the latest research. Julien explains why the meaning and purpose of a system must remain clear throughout the research process and why even advanced techniques provide little value when they are disconnected from the original question.

We also examine asset valuation from a deeper perspective. Market prices, accounting data, model outputs, textual signals, and AI-generated scores are all representations shaped by assumptions and constraints. Julien explores whether value can be understood as something structurally meaningful that remains consistent across multiple valid representations.

Finally, Julien discusses how he uses artificial intelligence in research and learning. Rather than treating AI as a source of automatic answers, he uses it as a rigorous analytical partner for exploring academic literature, challenging mathematical reasoning, identifying errors, and strengthening his problem-solving process.

A technical and philosophical conversation on quantitative research, mathematical modeling, complex systems, blockchain, asset valuation, artificial intelligence, and what it takes to build models that can be trusted in the real world.

 

*DISCLAIMER*

The information shared on this podcast is for educational and informational purposes only and reflects the personal opinions of the hosts and guests at the time of recording. Nothing in this podcast constitutes financial, investment, legal, tax, or trading advice, and nothing should be interpreted as a recommendation to buy, sell, or hold any security, cryptocurrency, derivative, or financial product.

Trading and investing involve substantial risk, including the possible loss of all or part of your capital. You are solely responsible for your own decisions, and you should consult a qualified professional before making financial decisions. By listening to this podcast, you agree that the hosts, guests, and producers are not liable for any losses or damages arising from the use of any information discussed.

Antonio Berenguer is an options trading and market-making professional with a background in engineering, mathematics, computational research, quantitative finance, and cryptocurrency markets.

Antonio completed a PhD in computational electromagnetics before moving into quantitative finance. After earning a master’s degree in Madrid, he joined an options market-making firm in Amsterdam, where he spent approximately six years working across liquidity provision, screen and broker trading, quantitative research, signal development, and position-taking strategies. He later moved into cryptocurrency trading and market making.

In this episode, Antonio joins us for an in-depth conversation about options market making, volatility trading, liquidity, hedging, position sizing, portfolio risk, and quantitative research.

Antonio explains how market makers generate returns by quoting bid and ask prices, capturing spreads, and managing inventory risk. We discuss how they adjust quotes, use correlated assets for hedging, and sometimes cross the spread when reducing exposure becomes more important than preserving their trading edge.

The conversation explores the complexity of options portfolios across different strikes and maturities. Antonio explains how Delta, Gamma, Vega, Vanna, Volga, and other Greeks help traders summarize risk, while also highlighting the limitations of Black-Scholes and the dangers of relying too heavily on simplified measures.

We also discuss position limits, correlation risk, internal netting, centralized Delta hedging, exchange rebates, quoting obligations, and how sophisticated firms reduce transaction costs by offsetting exposures across products and trading desks.

Antonio examines the gap between academic theory and practical trading. Elegant models may fail when liquidity is limited, hedges cannot be executed, or transaction costs remove the apparent opportunity. He shares a research process built around exploring data broadly, identifying promising relationships, and focusing only on signals that can realistically be traded.

Finally, we discuss crypto options, tokenized assets, and how blockchain technology may bring traditional and digital markets closer together.

A technical and practical conversation on options, volatility, market making, portfolio risk, quantitative research, liquidity, and the infrastructure behind modern financial markets.

 

*DISCLAIMER*

The information shared on this podcast is for educational and informational purposes only and reflects the personal opinions of the hosts and guests at the time of recording. Nothing in this podcast constitutes financial, investment, legal, tax, or trading advice, and nothing should be interpreted as a recommendation to buy, sell, or hold any security, cryptocurrency, derivative, or financial product.

Trading and investing involve substantial risk, including the possible loss of all or part of your capital. You are solely responsible for your own decisions, and you should consult a qualified professional before making financial decisions. By listening to this podcast, you agree that the hosts, guests, and producers are not liable for any losses or damages arising from the use of any information discussed.