Paul Bilokon is a veteran quant, educator, and entrepreneur with experience across major banks and systematic trading.

In this episode, we go deep into what actually makes research deployable: building a backtesting framework you can trust, cleaning and normalizing data correctly (rolls, corporate actions, microstructure effects), and stress-testing strategies against execution lags, transaction costs, and market impact.

We also discuss how Paul thinks about critical thinking as a repeatable research process, why he prefers starting with simple baselines before escalating model complexity, and where reinforcement learning and neural networks fit in finance when explainability and production constraints matter.

*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.

A sit-down with Raffaele Ghigliazza, a quant with a PhD background in mechanical engineering and deep work across applied math, dynamical systems, and neuroscience. He has spent about 20 years in finance, split between risk and asset management, and currently works as a macro-systematic researcher.

We discuss quant research after LLMs: what LLMs really changed, how to think about backtesting, and why robustness matters more than ever. Topics include business cycles, data limitations, overfitting, CPCV and cross-validation, ensembling, and why mixing market regimes can break a model.

*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.

Episode 8 with Orlando explores where market models work and where they fail, especially in credit markets where pricing is less observable, and data is often dirty. We cover how to find edge through data cleaning, why end-of-day pricing can mislead risk systems, and how to think about VaR and stress testing when liquidity shifts. We also discuss the limits of the Black-Scholes model for long-dated or far-from-the-money options, how Orlando builds a meritocratic research team, and what it takes to scale from an emerging fund to an institutional one.

*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.

Episode 7 features Matthias Bouquet, a quant who moved from a computer vision PhD into asset management, prop trading, banks, and hedge funds across Tokyo, London, and Singapore.

We cover why market ML is harder than vision, how overfitting shows up, and what actually helps in practice: solid validation, simpler models, better features, and strict risk management.

He also explains an options lens on volatility and skew, real-world trading frictions such as slippage, fills, and outages, and how LLMs can accelerate research without replacing discipline.

*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.

In Episode 6, we host Meir Barak, a veteran day trader, author, and the founder and chairman of Tradenet, where he focuses on building structured training programs for traders worldwide. We discuss what his day-to-day work looks like, including turning market behavior into repeatable frameworks, prioritizing risk discipline, and developing traders through process.

*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.

Marco Santanché, founder of Unbiased Alpha, joins the show to unpack what truly matters in quantitative research. We explore the key differences between institutional and retail trading, the real risks behind CFDs and leverage, and how quants turn vague client objectives into clear, actionable KPIs. The conversation also dives into realistic backtesting, why overfitting is so common, and when machine learning genuinely adds value in trading.

*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.

A sit-down with Jared Broad, CEO of QuantConnect, to unpack how one platform turned quant research, backtesting, and live execution into an end-to-end workflow. Jared explains why QuantConnect went open source in an industry that usually keeps everything secret, and why hedge funds waste years rebuilding the same infrastructure instead of focusing on alpha.

We break down what makes Lean “institutional-grade,” including its plugin architecture for brokerages, fees, and datasets, as well as the complex engineering behind corporate actions, ticker changes, and extended historical coverage. Jared also shares how QuantConnect validates data quality by cross-checking vendors, running automated “spiders", and using human review when needed.

*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.

A focused conversation with Oren Tapiero, a quantitative researcher at Tidal, on how machine learning is truly used in live trading. The discussion covers why the research question matters more than the model itself, how to approach feature engineering and causality instead of simple correlation, and why walk-forward backtesting and regime awareness are essential. A clear, reality-driven perspective on ML for quants who care about what actually works.

*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.

Oz Pirvandy is a Tel Aviv-based systematic fund manager and the founder of Elevate Algo Fund. With a background across economics, political science, mathematics, and data science, Oz brings a research-driven approach to portfolio construction, shaped by both academia and real-world experience in banks, where risk management is the primary priority.

In this episode, Oz explains why the S&P 500 works as an algorithmic benchmark and what most investors miss about its mechanics: concentration, index rules, and the tradeoff between rebalancing frequency and costs. We discuss his framework for building portfolios by ranking opportunities by risk-adjusted return, then adding positions based on low correlation; why he prefers partial rebalancing; and why keeping meaningful cash reserves is essential for both protection and flexibility. We finish with his view on 2026 and his plan to launch a second, more flexible multi-strategy fund around mid-2026.

*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.

Ryan Ling is a London-based systematic short-term interest rate (STIR) trader. Ryan studied Mathematics and Data Science, blending statistics and computer science, and has built his career across several parts of quantitative trading. He began in banking, structuring and exotics, then moved into crypto trading, including market-making and HFT, before transitioning into interest rate futures.

In this episode, Ryan explains what market making really involves, how traders monitor high-speed algorithms in real time, and why the job often feels more like art than science when you are reacting to flow and managing adverse selection. We also discuss where data analysis and machine learning actually add value in practice, which is often after the fact through post-mortems that help teams understand what happened and improve execution. The conversation also touches on why OTC trading still matters, how competition changed crypto spreads, and a forward-looking idea Ryan finds compelling: the emergence of tradable markets for AI compute and what it might take to make them liquid.

*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.