As traders, we scour the internet, books, and articles for industry specific information to create our new fancy algorithms. The Black-Scholes model, Markowitz Mean-Variance portfolio optimization, the Capital Asset Pricing Model (CAPM)… These are all systems designed for investment purposes(...)
We wrote a lot about transformers in the last three blog posts. Their sole purpose was for feature transformation / importance weighting. These transformed and attention-weighted features will be used as input to downstream applications. In this blog post, we will discuss one such application:(...)
Over the past decade and a half, the US equities have set the hard-to-beat performance benchmark. Nearly all of the other countries, no matter if small or big, emerging or developed, have lagged behind. However, what are the forces behind this outperformance? Why did most of the other markets and(...)
Skewness is a measure of the asymmetry of a return distribution. In this post, I’ll discuss the skewness risk premium and how skewness can be used to forecast realized volatility. Skewness Risk Premium in the Options Market Skewness of returns is a statistical measure that captures the asymmetry of(...)
Valuation models for equity indexes are essential tools for investors seeking to assess long-term market conditions. Traditional models like the CAPE ratio, introduced by Robert J. Shiller, or the Buffett Indicator often rely on macroeconomic variables such as corporate earnings or GDP. While(...)
When I sat down recently with Cesar Alvarez of Alvarez Quant Trading, I knew I'd be tapping into a deep reservoir of quantitative trading wisdom. Cesar’s journey into systematic trading began similarly to many of us—starting with discretionary trades, dabbling in mutual funds, and eventually(...)
Recently on QuantStart we have begun looking at generating synthetic asset price paths using Stochastic Differential Equation models such as the Brownian Motion, Geometric Brownian Motion (GBM), Ornstein-Uhlenbeck and Vasicek Models. Historically, we have also considered more sophisticated models(...)
Someone sent me their trading technology blueprint. It was a thing of beauty: timeseries databases, Grafana dashboards, message queues, and all sorts of fancy architecture. My first question: “What are you currently trading?” Their answer: “Nothing yet. But I’m planning a medium frequency stat arb(...)
Paul Calluzzo, Fabio Moneta, and Selim Topaloglu, authors of the April 2025 study “Momentum at Long Holding Periods” investigated a key aspect of how academic momentum strategies are typically constructed when forming a portfolio. Specifically, at the end of each month t−1, the standard 12-2(...)
“A single hair from the head of a woman is worth more than all the books of Galen and Avicenna.” Paracelsus. Paracelsus (1493–1541) was one of the most radical and influential physicians and philosophers of the Renaissance. A restless traveler, alchemist, and fierce critic of medical orthodoxy, he(...)
Standard portfolio allocation algorithms like Markowitz mean-variance optimization or Choueffati diversification ratio optimization usually take in input asset information (expected returns, estimated covariance matrix…) as well investor constraints and preferences (maximum asset weights, risk(...)
An easy, practical way to harness an edge in the face of trading costs is the “no trade region” technique. It nearly always improves after-cost performance. Here’s a real example: And it does so with only one-tenth of the trading of the baseline strategy! Uncertain edge vs certain costs A good(...)
In the previous blog post, we saw how we can apply self-attention transformers to a matrix of time series features of a single stock. The output of that transformer is a transformed feature vector r of dimension 768 × 1. 768 is the result of 12 × 64: all the lagged features are concatenated /(...)
The ratio of gold prices to other asset classes has been shown to be a useful predictor of stock market returns. In this post, we discussed several gold-based ratios and how they can be used to forecast equity market performance. Gold Oil Price Ratio As a Predictor of Stock Market Returns Analyzing(...)
We’ve previously examined how central bank policy decisions—particularly those by the Federal Reserve and the European Central Bank (ECB)—impact stock market behavior. The price drift in U.S. equities around the Federal Open Market Committee (FOMC) meetings is a well-documented phenomenon.(...)
We often have baskets of assets that we turn into trading strategies. But also, we have baskets of trading strategies that we need to allocate our capital into. In my last post (here), I demonstrated how to use generative AI to create a theoretically limitless supply of trading strategies. But,(...)
I'm now in full book writing mode, so I don't have the time to do full blog posts. Instead I plan to do a series of quick posts where I share some research I did for the book. Cynically, there is also a chance it will encourage you to buy the book, as long as I don't overshare like(...)
You are observing the markets in real-time—thousands of price ticks cascading across your screen, each reflecting a momentary shift in supply, demand, and sentiment. At first glance, the data appears evenly spaced, structured, and regular. Yet beneath this surface lies a deeper asymmetry: the(...)
Older people among my readers will remember the time when there was – for a while – a discussion about how the US stock market had significantly higher returns between yesterday’s close and today’s open (when there were no trades at all) than during the day. Those were the innocent days of an era(...)
The volatility of volatility index, VVIX, is a measure of the expected volatility of the VIX index itself. In this post, we will discuss its dynamics, compare it with the VIX index, and explore how it can be used to characterize market regimes. Dynamics of the Volatility of Volatility Index, VVIX(...)
Hello all, Welcome to the Quantpedia Awards 2025 winners announcement. This is the moment we all have been waiting for, and today, we would again like to acknowledge the accomplishments of the researchers behind innovative studies in quantitative trading. So, what do the top five look like, and(...)
As mentioned in my last post (here), I designed and developed a way to quickly produce trading systems with the help of generative AI. And while this sounds like a recipe for disaster, because I constrained the problem to a very specific subset and I focused on only a few factors, the results were(...)
In two of our previous articles, we explored the idea of using artificial intelligence to backtest trading strategies. Since then, AI has continued to develop, with tools like ChatGPT evolving from simple Q&A assistants into more complex tools that may aid in developing and testing investment(...)
Previously, we have discussed classical non-parametric approaches to making probabilistic inferences on attributes of trading strategies based on typical artefacts available. In this post, we discuss and implement in Python a finite-sample probabilistic bounding method, a unique approach coined(...)
You start writing a trading strategy. The entry? Solid. Sharp. Thought-out. The exit? Let me guess… Fixed dollar profit target? A stop based on some ATR multiple? Maybe a hard-coded dollar loss? Or the classic: "Just close it after 7 bars… I guess?" Same old, same old. What if that’s your(...)
Christian Goulding and Campbell Harvey, authors of the study “Investment Base Pairs,” proposed a groundbreaking framework for portfolio construction that challenges traditional approaches in modern finance. Their research focused on leveraging cross-asset information to optimize investment(...)
The electronic marketplace generates vast amount of data—billions of timestamped trades, quotes, and cancellations—that demand processing to extract actionable insights. For quantitative traders, the central challenge lies not in designing strategies but in constructing a robust framework to(...)
When it comes to trading system design, there are two schools of thought: one advocates for simpler rules, while the other favors more complex ones. Which approach is better? This newsletter explores both perspectives through the lens of machine learning. Use of Machine Learning in Pairs Trading(...)
Often as traders, we equate complexity with profitability. A model’s edge comes from it doing something that no other person on Earth has tried yet. But the data shows that simple rules based on real market factors still outperform most models. Those that continue seeking complexity are headed(...)
My kids love bedtime stories. Like most kids. But they’re not into fairy tales or superheroes. They’re obsessed with one thing: “Dad, can you tell a witch story? A mean witch, okay?” Every night. Same request. So I lie next to their bed and say, “Alright, buddies. A mean witch story it is.” Now, I(...)
Someone recently asked me if I have a checklist for adopting new trading strategies. You know, a neat little formula like “if backtested Sharpe > 1.8, trade it” or “if drawdown < 15%, green light.” I get the appeal. We all want clear, objective criteria to make these decisions easier. But(...)
In the previous blog post, we gave a very simple example of how traders can use self-attention transformers as a feature selection method: in this case, to select which previous returns of a stock to use for predictions or optimizations. To be precise, the transformer assigns weights on the(...)
Everyone either naively thinks that an LLM will find alpha for them, or equally naively thinks LLMs cannot develop their own systems with any sort of edge. The reality is quite the opposite. When used properly, LLMs can supercharge your strategy research process by at least 10x. Those who aren’t(...)
Risk parity is an investment strategy that allocates risk exposure equally across asset types through volatility-based calibration and leverage. A most profitable risk parity strategy in the past decades has been the equity-duration “long-long”, which harvests combined equity and long fixed-income(...)
Questions about this long-ago strategy from Cliff Smith land in our inbox periodically (here’s another recent take). Smith’s simple strategy trades senior loan (aka leveraged loan) ETFs like BKLN, and has continued to be effective at timing these ETFs in the 10+ years since it was published. We’ve(...)
When building an intraday systematic strategy, the quality and consistency of historical data can make or break your trading results. Cost, however, is also a critical factor for many traders. We conducted a comprehensive analysis comparing three popular data providers offering REST APIs for(...)
In the day-to-day grind of systematic trading, volatility isn’t just a market feature—it’s the atmosphere we operate in. It drives the edge, defines the risk, and sets the tempo. But while volatility creates the conditions for profit, it also contains the seeds of our destruction. That(...)
Building machine learning models for trading is full of nuances, and one important but often overlooked question is: what exactly should we try to predict—the direction of the next market move or the actual value of the asset’s return? A recent paper by Cheng, Shang, and Zhao, titled “Direction is(...)
During the previous optimization cycle, I was tasked with enhancing inventory management protocols for a legacy trading system operating under low-latency constraints—order cycle times ≥ 500ms. While the academic corpus fixates on high-frequency trading paradigms—microsecond latency optimization,(...)
Oscillator-type indicators swing around the zero line. They are often used for opening positions when oscillator exceeds a positive or negative threshold. In his article series about no-lag indicators, John Ehlers presents in the TASC June issue the Cybernetic Oscillator. It is built by applying a(...)
The recent market turbulence highlights the need for improved risk management and strategies to reduce portfolio volatility. In this post, I’ll explore how to enhance portfolio diversification using low-volatility stocks. Gold and Low-Volatility Stocks as Diversifiers Gold has long been regarded as(...)
For those of us who grew up before GenAI became a thing (e.g. Ernie), we often use tree-based algorithms for supervised learning. Trees work very well with heterogeneous and tabular feature sets, and by limiting the number of nodes or the depth of a branch, there is feature selection by default.(...)
A friend of mine owns a Neapolitan-style pizzeria… this is the real pizzeria… When he first opened, he had one recurring headache: He could never guess how many pizzas he’d sell each night. Some days he ran out of dough by 9pm. Other days he overprepared and ended up tossing dozens of unused bases.(...)
Rethinking the Stock-Bond Correlation Thierry Roncalli (Amundi Asset Management & University of Evry) February 2025 The stock-bond correlation is a basics of finance and is related to some of the fundamentals of asset management. However, understanding the stock-bond correlation is not easy. In(...)
What can we realistically expect from investing across different asset classes over the long run? That’s the kind of big-picture question the “Long-Run Asset Returns“ paper tackles—offering a sweeping look at how stocks, bonds, real estate, and commodities have performed over the past 200 years.(...)
In his 2013 paper “The Other Side of Value: The Gross Profitability Premium,” Robert Novy-Marx documented that profitability, broadly measured, has as much power as relative price in predicting cross-sectional differences in expected returns. With the publication of that paper, profitability(...)
Algorithmic trading systems can give you this sleek, high-tech confidence—like the robots have everything under control. They’re fast, precise, and backtested to death, right? But that’s where the trap snaps shut. When your risk metrics are built on things like standard deviation or recent(...)
Can machine learning models better predict stock returns if they are tailored to specific industries, or is a one-size-fits-all (generalist) approach sufficient? This question lies at the heart of a recent research paper by Matthias Hanauer, Amar Soebhag, Marc Stam, and Tobias Hoogteijling. Their(...)
In the realm of investment strategies, simplicity has long been favored. Traditional models with a limited number of parameters are prized for their interpretability and ease of use. However, recent research challenges this convention, suggesting that embracing complexity can lead to more accurate(...)