[Back to Intro]







20/12/2022 ADIA Lab Can Factor Investing Become Scientific? ADIA Lab Seminar Series The ADIA Lab Seminar Series aims to explore the latest trends and technologies in Data Science, Artificial Intelligence, Machine Learning, and High-Performance Computing across all major fields of study.
02/12/2022 ADMO ADIA Lab announces Advisory Board, academic collaborations and inaugural research award on first day of operations Abu Dhabi Media Office ADIA Lab, the independent research institute dedicated to basic and applied research in data and computational sciences, commenced operations today, the 51st National Day of the UAE. As part of its launch, the Lab announced the composition of its Advisory Board, the details of its first academic collaborations, and launched a US$ 100,000 research award.


Kilburn, Faye 'Corrective' algo tells quant firm when it's wrong


"The idea of corrective AI, also known as meta-labelling, was developed by Marcos Lopez de Prado, an expert machine learning."


England, Andrew Abu Dhabi Wealth Fund bets on scientific approach using quant experts

The Financial Times

Among the recruits is Marcos Lopez de Prado, a professor and quant expert at Cornell University, who is global head of quantitative research and development at ADIA


Mannix, Rob ADIA wealth fund is building supergroup of quant investing


Other quants say the idea is captivating. “I find it fascinating; a lot of interesting stuff should come out,” says Jean-Philippe Bouchaud, the chairman of Capital Fund Management. If he had the time and the money, he’d try something similar, he says



Cornell Engineering "Buy-Side Quant of the Year": CFEM Professor Marcos López de Prado and Collaborator Alex Lipton Earn Highest Honors in Risk Awards 2021

Cornell University

"Marcos López de Prado and Alex Lipton have been named Buy-Side Quant of the Year in the Risk Awards 2021 for their contributions towards solving the problems of stop-loss and profit-taking in optimal trading."


Abu Dhabi Investment Authority Marcos Lopez de Prado and co-author named Quants of the Year at Risk Awards 2021


"Dr. Marcos Lopez de Prado, Global Head - Quantitative Research & Development in ADIA’s Strategy & Planning Department, has been named Buy-Side Quant of the Year by Risk.net, alongside his co-author Dr. Alexander Lipton, a professor at the Hebrew University of Jerusalem and a Connection Science Fellow at the Massachusetts Institute of Technology."


Risk.net Staff Buy-Side Quant of the Year: Alex Lipton and Marcos Lopez de Prado


"The problem of estimating stop-loss and profit-taking levels is normally solved by two separate models using the circuitous route of Monte Carlo simulations. But work published this year by Alex Lipton and Marcos Lopez de Prado takes a novel, more direct tack."


Bajet, Roselle  Professor López de Prado Appointed Global Head of Quantitative Research and Development

Cornell University

"The Abu Dhabi Investment Authority (ADIA), one of the largest sovereign wealth funds, has announced that it has appointed Marcos López de Prado as Global Head of Quantitative Research and Development."


Cesa, Mauro Lipton and de Prado on Covid-19 and optimal trading strategies

Risk Magazine

"While reading de Prado’s book on quantitative investments, Lipton saw the possibility of solving an open question in that volume using a technique called heat potentials. “I got in touch with Marcos and we decided to work on that,” recalls Lipton. When Covid struck, they decided to work together to model the pandemic too."


Nguyen, Lili The Future is Bright... for those who survive


"Asset managers should focus their efforts on researching theories, not backtesting trading rules [...] Only a theory can establish the mechanism that causes the patterns that the strategy is presumably profiting from."


Nguyen, Lananh Is that a Robot at My Desk? How to Survive on Wall St

The Washington Post

"Even the highest-paid jobs for portfolio managers could disappear as firms use data scientists to solve some of the most complex investment problems, according to Marcos Lopez de Prado, a Cornell University professor and the former head of machine learning at AQR Capital Management LLC. Many of the 6.1 million people employed in the finance and insurance industries will lose their jobs because they aren't trained to work alongside algorithms, Lopez de Prado said."


Gunia, Amy 'It's a Matter of When.' How Machines Are Taking Over the World's Stock Markets

Time Magazine

"There is no reason to not expect that eventually these machines will be able to solve many tasks that we cannot solve. It’s a matter of when, it’s not a matter of if."


Nguyen, Lananh Robots in Finance Could Wipe Out Some of Its Highest-Paying Jobs

Bloomberg News

"Financial machine learning creates a number of challenges for the 6.14 million people employed in the finance and insurance industry, many of whom will lose their jobs -- not necessarily because they are replaced by machines, but because they are not trained to work alongside algorithms,” Lopez de Prado told the U.S. House Committee on Financial Services."


Gang, Yaelle The benefits of crowdsourcing investment research

Canadian Investment Review

"There’s a crisis in financial research because of statistical shortfalls, says Marcos López de Prado, a professor of practice at Cornell University’s school of engineering and chief investment officer of True Positive Technologies."


Lee, Justina The Master of Robots Left AQR. Now He's Coming for Wall Street


"The man dubbed the world’s top quant has a message for Wall Street firms lavishing millions on machine-learning programs: Most of you are doing it wrong."


Campanelli, Sondra López de Prado Launches ML Firm to Tackle Hedge Fund Underperformance, Fees


"Individual economic factors do not work equally well under all financial regimes. There are no all-weather factors, and it is important to weight factors according to their idoneity under the prevailing financial regime. Recognising those regimes requires machine learning techniques."


Mannix, Rob Some Quant Shops Doomed to Struggle -- López de Prado


"Quant shops that stick too stubbornly to theory when devising strategies will trail behind maths-driven “empiricists” who analyse data with no preconceptions. That’s according to Marcos López de Prado, the former head of machine learning at AQR and founder of a new venture that aims to disrupt the traditional quant asset management business."


Nguyen, Lili A conversation with "Quant of the Year 2019" Marcos López de Prado


"Individual economic factors do not work equally well under all financial regimes. There are no all-weather factors, and it is important to weight factors according to their idoneity under the prevailing financial regime. Recognising those regimes requires machine learning techniques."


Cornell Engineering ORIE Adds Marcos Lopez de Prado to Cornell Financial Engineering Manhattan

Cornell University

"We are delighted to welcome Marcos at CFEM. He has been instrumental in developing and advancing our Financial Data Science certificate, and he brings over 20 years of quant experience into our classroom,” said Victoria Averbukh, Director of CFEM. "Before formally joining CFEM, Professor Lopez de Prado taught his graduate course 'Advances in Financial Machine Learning' as a CFEM practitioner."


Kilburn, Faye Baselines for applying machine learning to investing


"The newly founded quarterly Journal of Financial Data Science offers some guidance on this score. The journal, created to address the relatively poor track record of algorithms in forecasting, is edited by Joseph Simonian, director of quant research at Natixis Investment Managers, Frank Fabozzi, professor of finance at the Edhec Business School, and Marcos Lopez de Prado, a principal at AQR Capital Management."


Basak, Sonali et al. AQR Head of Machine Learning Set to Leave After Seven Months


"[T]he firm bought certain intellectual property owned by Lopez de Prado, including multiple patent applications related to machine learning [...] Lopez de Prado will remain at AQR for a short period of time to help with the transfer of his technologies to the firm, according to the statement. He plans to use the proceeds from his sale of IP rights to launch a firm, which will develop machine learning algorithms for institutional investors, according to a person familiar with his thinking."


Lopez de Prado, Marcos Fund industry must use the right type of machine learning

The Financial Times

"We need ML to develop better financial theories and we need financial theories to restrict ML’s propensity to overfit. Without this theory-ML interplay, investors are placing their trust on high-tech horoscopes."


Tuttle, Beecher The most intelligent man in finance made this unfortunate prediction about quant jobs


“Your firm must set up a research factory, where tasks of the assembly line are clearly divided into subtasks, where the role of each quant is to specialize in a particular subtask.”


Instance, Rosie The Journal of Portfolio Management names Marcos Lopez de Prado "2019 Quant of the Year"

The Journal of Portfolio Management

“For many years, Marcos has led the way towards the adoption of machine learning techniques in finance,” said Frank J. Fabozzi, Editor of JPM. “His many publications have introduced innovative ways of thinking about financial problems and solving them in practice. Our ‘Quant of the Year’ award recognizes the totality of work by a researcher, and I think Marcos’ name was in everyone’s mind from the onset of the selection process.”


Buerkle, Tom Welcome the new AI investment overlords


"Hedge fund AQR recently hired prominent data scientist Marcos Lopez de Prado to spearhead its machine-learning efforts."


Baert, Rick Believers say AI could soften market volatility, not amplify it

Pensions & Investments

Quantitative trading that already relies heavily on AI "has improved liquidity conditions by reducing bid-ask spreads and microstructural volatility" — the volatility associated with price discovery, said Marcos Lopez de Prado, principal and head of machine learning at AQR Capital Management LLC, Greenwich, Conn.


Schatzker, Erik  AQR Accepts 0.8% of Job Seekers as Firm Ramps Up Hiring in 2018


Of the more than 35,000 people who applied to the Greenwich, Connecticut-based firm in 2018, only 270 got jobs, according to AQR. That acceptance rate -- just 0.77 percent -- is below the 4 percent that Goldman Sachs Group Inc., widely considered the choosiest of the big Wall Street banks, reported in 2017 [...] AQR’s senior-level recruits in 2018 include Marcos Lopez de Prado, formerly with Guggenheim Partners and now head of machine learning; and Howard Mansell, who left Facebook Inc. to become head of research engineering.


Butcher, Sarah The 20 top people in machine learning and data science in finance


Some ML researchers working in finance.


Walker, Owen NASA says quantum computing is the future for funds

Financial Times

"The use of quantum computing in the investment industry has been considered for several years, with Marcos Lopez de Prado, who recently left Guggenheim Partners for quant specialist AQR Capital Management, one of its biggest proponents."


Asmundsson, Jon The Big Problem With Machine Learning Algorithms

Bloomberg Markets

“Machine learning algorithms will always identify a pattern, even if there is none,” he says. In other words, the algorithms can view flukes as patterns and hence are likely to identify false strategies. “It takes a deep knowledge of the markets to apply machine learning successfully to financial series,” López de Prado says.


Schatzker, Erik

Quant Investor Cliff Asness Hasn’t Smashed His Screen This Year—Yet

Bloomberg Markets

"We’ve just made a big hire in machine learning, Marcos López de Prado. We’ve been doing versions of machine learning here in isolated groups for a while, but now it’s such a big effort. We think it has applications across a ton of what we do. One of the reasons we were comfortable hiring Marcos is that he’s very comfortable with trying to fuse machine learning with a need for some economics behind it. He’s not a “just let the machines run wild” guy."

"[...] I think we just hired a howitzer. Processing the big data first—which is what Marcos is about—if you’re marginally better at it, can be a marginal advantage forever."


Williamson, Christine

AQR hires head of machine learning

Pension & Investments

"Innovation and research are at the core of what we do, driving us to develop diversifying solutions to meet our clients' evolving needs. With a distinguished academic background and values consistent with ours, we look forward to partnering with Marcos to enhance our machine-learning initiatives," said David G. Kabiller, co-founder, in the release.


Burger, Dani

AQR Builds Machine-Learning Strength Via Lopez De Prado Hire

Bloomberg News

"AQR Capital Management has appointed a head of machine learning for the first time in its two-decade history. Marcos Lopez de Prado is joining the $226 billion money manager to fill the freshly created role, according to a Wednesday statement. He left Guggenheim earlier this year after building their proprietary quantitative-strategy business, departing along with his team at the time."



AQR Appoints Head of Machine Learning Group


"AQR Capital Management, LLC (“AQR”), a global quantitative investment management firm, today announced that Marcos López de Prado has joined the firm as a Principal and Head of Machine Learning. As Head of Machine Learning, Marcos will be part of AQR’s research and portfolio management teams and will focus on further developing the machine learning tools and techniques used at the firm."


Lopez de Prado, M.

Finance in the Age of Machine Learning, Parts 1 to 6

TABB Forum

Machine learning algorithms will transform how everyone invests for generations. While the most popular potential use of ML is predicting prices, this series explores alternative uses of ML in finance.


Low, R.; Li, T. and Marsh, T.

BV-VPIN: Measuring the Impact of Order Flow Toxicity and Liquidity on International Equities Markets


"We find that a rise in BV-VPIN effectively foreshadows high-levels of volatility in the equities indices of several countries. If a BV-VPIN futures contract exists, we show that it would exhibit safe haven characteristics during market downturns. In particular, a simple active portfolio management strategy that times investments in equities (risk-free asset) when BV-VPIN levels are low (high) outperforms a buy-and-hold strategy. Thus, we find support for the application of BV-VPIN in international equities."


Crosman, Penny

Why banks like Barclays are testing quantum computing

American Banker

"True Positive Technologies, which creates investment strategies for institutional investors with the use of machine learning, has been working with quantum computers since 2014 for portfolio optimization and scenario simulations. Dr. Marcos Lopez de Prado, who founded Guggenheim Partners’ Quantitative Investment Strategies business and is now CEO of True Positive, argues that quantum computing will solve financial firms' need for increased computing capacity in the future, while requiring less energy than traditional computers suck up."


Steenbarger, B.

The Growing Crisis in Modern Finance


An interview on why most research findings in financial economics are false, and the implications for investors.


Guggenheim Partners

Statement From Guggenheim Partners Regarding Quantitative Investment Strategies Unit


"Guggenheim Partners today agreed to transfer its Quantitative Investment Strategies (“QIS”) unit to Dr. Marcos Lopez de Prado, who built that business and its technology as a Senior Managing Director of Guggenheim."


Wigglesworth, Robin

Renaissance, DE Shaw look to quantum computing for edge

Financial Times

Marcos Lopez de Prado, a quant researcher and fellow at the Berkeley Lab, says: “You need to decode markets and find the invisible patterns. The people that do that best have the best models and the most powerful computers. It gives you an edge. It's amazing what we could do with quantum computers."


Segal, J.

How Universities Are Failing Finance Students

Institutional Investor

"The presence of financial academia is fading, something that was unthinkable 10 years ago," writes López de Prado. "The edge is not yet another reincarnation of the capital asset pricing model [...] FinTech, big data, machine learning, and even quantum computing will render formal finance education even more irrelevant, he believes."


Asmundsson, J.

Quantum Computing Might Be Here Sooner Than You Think

Bloomberg Markets

Marcos López de Prado, a senior managing director at Guggenheim Partners LLC who’s also a scientific adviser at 1QBit and a research fellow at the U.S. Department of Energy’s Lawrence Berkeley National Laboratory, says it’s all about context. “The reason quantum computing is so exciting is its perfect marriage with machine learning,” he says. “I would go as far as to say that currently this is the main application for quantum computing.”


Hope, B.

The Quants Run Wall Street Now

Wall Street Journal

"Guggenheim Partners LLC built what it calls a “supercomputing cluster” for $1 million at the Lawrence Berkeley National Laboratory in California to help crunch numbers for Guggenheim’s quant investment funds, says Marcos Lopez de Prado, a Guggenheim senior managing director. Electricity for the computers costs another $1 million a year."


Melin, M.

JPMorgan: Hierarchical Risk Parity Portfolio Building Method Beats Markowitz


"Harry Markowitz’s modern portfolio theory has been a staple concept among many noncorrelated portfolio builders [...] JPMorgan’s Quantitative and Derivatives Strategy team thinks there is a better method to construct portfolios [...] In the studies, the HRP portfolio method outperformed based on several noncorrelated standards."


Bauer, M.

Quantum computing is going commercial with the potential to disrupt everything


Comments on IBM's announcement that they will produce a commercial quantum computing, with services delivered via cloud.


Steenbarger, B.

Reason And Rationality: The Psychological Keys To Investing Success


"A remarkable post recently appeared on Google Plus. A quiet researcher in mathematical finance who manages a large portfolio decided to speak out."



D-Wave Systems Launches Quantum for Quants Online Community

Inside HPC

Launch of QuantumForQuants.org.


Dawes, T.

D-Wave launches Quantum for Quants at Budapest derivatives conference

CanTech Letter

Launch of QuantumForQuants.org.


Thomas, Z.

Quantum computing: Game changer or security threat?


A BBC discussion on the future of quantum computing.


Mack, B.

What can Quantum Computing achieve for Quants?

Global Derivatives

An interview on financial applications of quantum computing.


Cater, S.

Machine learning with Marcos Lopez de Prado

Global Derivatives 2016

An interview on Machine Learning applications to investing.


Zweig, J.

Chasing Hot Returns in ‘SmartBeta’ Funds Can Be a Dumb Idea

Wall Street Journal

Because computers and access to data are proliferating, the odds that strategies are based on “statistical flukes without theoretical support” is rising, warns Marcos López de Prado, a senior managing director at Guggenheim Partners, an investment firm in New York that manages about $240 billion. “For now, our best shot is to educate the public,” he says, “because not everyone in the industry is going to come clean.”


Clark, J. and S. Kishan

Quantum Computers Entice Wall Street Vowing Higher Returns

Bloomberg News

Bloomberg features a recent paper with Peter Carr (Courant Institute), Kesheng Wu (Berkeley Lab) and scientisits from 1QBit.

06/01/2015 Orr, L. The Backtesting Crisis Chief Investment Officer "Managers who cherry-pick for optimal results aren’t even the worst abusers, argues Guggenheim’s top quant."
05/27/2015 Automated Trader Machine Learning is the new C++ Automated Trader Article on Global Derivatives 2015's round table about Big Data.
04/26/2015 Bailey, D. and J. Borwein Lessons from the “Flash Crash” regulatory fiasco The Huffington Post "[...] Regulators have admitted that the Flash Crash was due to order imbalance, as Easley et al. had explained five years earlier."
04/06/2015 Hope, B. How Computers Trawl a Sea of Data for Stock Picks Wall Street Journal Professors from University of California, Davis, and several other institutions warned in an April 2014 research paper of a trend of “overfitting” in math-based trading by hedge funds and other money managers, in which random correlations are interpreted wrongly as strong relationships. They concluded that “pseudo-mathematics” and “financial charlatanism” were running rampant on Wall Street. Such bad math, they wrote, “is a large part of the reason why so many algorithmic and systematic hedge funds do not live up to the elevated expectations generated by their managers.”
03/09/2015 Scott, C.

Journal of Portfolio Management Announces Advisory Board Member

Journal of Portfolio Management

"The Journal of Portfolio Management (JPM) announces that Marcos López de Prado, Senior Managing Director at Guggenheim Partners and Research Fellow at Lawrence Berkeley National Laboratory, has been named to the Journal’s Advisory Board, effective March 1, 2015."

02/25/2015 Bershidsky, L.

Russia's Insider Traders Know Putin's Plans


"On Feb. 27 the VPIN for the RTS index spiked, reaching 52.5 percent -- way above the norm [...] March 3 was the first trading day after Saturday, March 1 -- the day Crimea's new, pro-Russian local government asked Russia for help in "securing peace" and Putin asked his rubber-stamp Parliament for permission to send troops to Ukraine. The RTS index dropped 12 percent as the rest of the market caught up with the insiders..."

01/27/2015 Scott. C. Practical Applications of The Deflated Sharpe Ratio Institutional Investor Journals A Q&A on backtest overfitting and how to deflate the Sharpe ratio.
01/16/2015 Bengani, P. Fiddling with figures Automated Trader Automated Trader features our work on backtest overfitting.
10/30/2014 Regan, Michael Beware Overfitting Models Even if They Win Baseball Bets Bloomberg News An article intoducing readers to our Backtest Overfitting web application.
10/25/2014 Blumenthal, Robin; Salzman, Avi Ghost in the Machine Barron's A quote regarding Prof. Harvey's revolutionary paper on cross-sectional returns and multiple-testing.


Scott, Cathy

El-Erian, Bogle, Malkiel Among 30 Luminaries Discussing Hot-Button Issues in Finance

Business Wire

"What do the top luminaries in finance really think about smart beta, momentum investing, performance inflation and the ability to predict stock market crashes? Thirty well-recognized luminaries have written their frank assessment of these burning issues, and much more, for The Journal of Portfolio Management’s 40th Anniversary Issue."


Zweig, Jason

Huge Returns at Low Risk? No So Fast: The wild world of 'backtesting' -- and why investors need to be on guard.

Wall Street Journal

WSJ features our research on backtest overfitting.


Rekenthaler, J.

Voodoo Investment Strategies Morningstar

A nice essay on our work on backtest overfitting.


Jacobs, Ryan

The Dangerous Mathematical Con of Hedge Funds and Financial Advisers

Pacific Standard

"Using too many trials to design investment algorithms renders them statistically useless and potentially devastating."


Institutional Investor Journals

Interview with Dr. David H. Bailey

Institutional Investor Journals

IIJournals interviewed David H. Bailey at the conclusion of our presentation at the Battle of the Quants 2014.


Conway, B.

Is a too perfect ETF backtest fraud?


“If an investment process is driven by what looks good historically, there’s a greater chance the attractive-looking result is just a fluke.”


Foley, S.

When use of pseudo-maths adds up to fraud

Financial Times

“By calling it fraud, the academics command attention, and investors would be wise to beware. With interest rates about to turn, and a stock market bull run ageing fast, there have never been such temptations to eschew traditional bond and equity investing and to follow the siren sales patter of those who claim to see patterns in the historical data.”



Computer Models Often Use Unsound Math, Researchers Say

Bloomberg News

Bloomberg News article discussing our latest article at the Notices of the American Mathematical Society.

"[M]athematicians in the 21st century have remained disappointingly silent with the regards to those in the investment community who, knowingly or not, misuse mathematical techniques such as probability theory, statistics and stochastic calculus. Our silence is consent, making us accomplices in these abuses."



‘Smoke and mirrors’ strategy costing Mum and Dad investors billions

University of Newcastle

Press Release by the University of Newcastle on occasion of the publication of our paper on Backtest Overfitting.


American Mathematical Society

Press Release by the American Mathematical Society

AMS, ScienceDaily & Eurekalert

Press Release by the AMS on occasion of the publication of our paper on Backtest Overfitting.


Risk Magazine

Interview by Risk Magazine

Incisive Media

Interview published by Risk Magazine and the organizers of the Trading and Investment Risk 2014 Conference.


Algorithmic Finance

One Minute with Marcos Lopez de Prado

Algorithmic Finance

Interview published by the journal Algorithmic Finance.


Total Trading

HETCO’s Head of Quant Trading & Research Marcos Lopez de Prado at the Trading Show NYC 2013


A summary of my presentation at Trading Show NYC 2013.


Faille, C.

Doing Penance for the Draw-down


A nice summary of what the "triple penance rule" is about.


O'Hara, M. and D. Easley

Financial markets are at risk of a ‘big data’ crash

Financial Times

"Being fast is not enough. We, along with Marcos Lopez de Prado of the Lawrence Berkeley National Laboratory, have argued that HFT companies increasingly rely on “strategic sequential trading”. This consists of algorithms that analyse financial big data in an attempt to recognise the footprints left by specific market participants."


Murphy, B.

Enthought Introduces Enthought Canopy, a Python Analysis Environment for Scientific and Analytic Computing


Press release announcing the introduction of Enthought Canopy.


Krieger, L.

Supercomputers could generate early-warning system for stock market crashes

Mercury News

"[...] Using the lab's Cray XE6 "Hopper" supercomputer, the Leinweber team found one precursor to a flash crash that a supercomputer could identify. Called Volume-synchronized Probability of INformed trading, or VPIN, it detected an imbalance between buy and sell orders, and growing volatility, about 45 minutes before [the] crash".


Zweig, Jason

Could Computers Protect the Market From Computers?

Wall Street Journal

The Wall Street Journal reports on the collaboration between Lawrence Berkeley National Laboratory and the inventors of VPIN.



Sub-Committee on Automated and High Frequency Trading

U.S. Commodity Futures Trading Commission

The CFTC uses two of our papers in setting the legal definition of High Frequency Trading.


Lash, Herbert

Post 'flash crash' monitoring emerges at Berkeley


This Reuters article discusses how VPIN could be used to design dynamic circuit breakers.


Carver, Laurie

US regulators ask DOE lab to study flash-crash forecasting tool

Risk Magazine

Risk Magazine reports that U.S. regulators have asked a National Laboratory to study methods to prevent flash-crashes, VPIN being one of the options considered.


Carver, Laurie

OTC flash crash: Dealers consider risks of HFT invasion

Risk Magazine

Risk Magazine features VPIN as a possible way to prevent OTC flash crash.


Grant, Justin

Formula May Pave Way to Stopping Flash Crashes

Advanced Trading

Interview with "Advanced Trading" Magazine.


Demos, Telis

US panel on flash crash urges rule changes

Financial Times

Financial Times refers to Maureen O'Hara's research on the "flash crash".


Glaser, Linda

Stock market 'flash' crashes now predictable, thanks to Cornell-developed metric

Cornell Chronicle

Cornell University featured the VPIN papers in its newspaper.


Kardos, Donna

'Toxicity' Metric May Help Avoid Another Flash Crash: Study

Dow Jones

Richard Ketchum, chairman and chief executive of the Financial Industry Regulatory Authority, mentioned the VPIN study Friday during a meeting of the Joint CFTC-SEC Advisory Committee.


Mehta, Nina

`Toxic' Orders Can Predict Likelihood of Stock Market Crashes, Study Says

Bloomberg News

A formula for measuring how fast the best-informed traders increase their share of market volume may help regulators prevent crashes such as the May 6 plunge. It became the second most read news article that day.









Jaeger, Markus; Stephan Kruegel; Dimitri Marinelli; Jochen Papenbrock; Peter Schwendner

Understanding Machine Learning for Diversified Portfolio Construction by Explainable AI

Munich Reinsurance Company

"... we find that HRP better matches the volatility target, and shows better risk-adjusted performances."


Borochin, Paul; Stephen Rush

A Network Analysis of Information Diffusion in the Financial Sector

University of Miami

"We find that the VPIN network based on firm-specific informed trading predicts firm-specific risk and performance significantly better than the firm-specific return network."


Massot, M., S. Nawn and R. Pascual

Bulk Volume Classification Under the Microscope: Estimating the Net Order Flow

University of the Balearic Islands

"Supporting ELO’s (2016) claim that BVC relies on all sources of buying and selling pressure, we find that BVC renders more accurate estimates of the NOF than of the trade-based OI."



Registered clinical trials make positive findings vanish


Like in most experimental research areas, Financial studies should pre-register the trials to be conducted. Otherwise, empirical finance will become a pathological science, a collection of "cold fusion" claims.

06/09/2015 Jiang, J. Volume-Synchronized Probability of Informed Trading (VPIN), Market Volatility, and High-Frequency Liquidity Brock University St. Catharines, Ontario "Summarizing from our empirical research, we conclude that VPIN can be employed as an effective risk management tool and can be put into practice in the prevalent high-frequency trading mechanism of the current financial world."
05/03/2015 The Economist False Hope: Most trading strategies are not tested rigorously enough The Economist The Economist features Cam Harvey's excellent paper on backtesting, which in turn refers to our NAMS article (May, 2014), "Pseudo-Mathematics and Financial Chalatanism".
04/21/2015 Miedema, D. and S. Lynch Flash Crash Arrest Lays Bare Regulatory Lapses at All Levels Reuters In "The Microstructure of the Flash Crash", Profs. Easley, O'Hara and I explained how the flash crash of May 6th 2010 was caused by order imbalance. Our explanation contrasted with the official SEC-CFTC report, which blamed a large mutual fund's order of 75,000 futures contracts for the debacle (supposedly originated by Waddell & Reed). Five years after that event, the U.S. Department of Justice has finally filed criminal charges against a high-frequency trader for causing that order imbalance:

"His conduct was at least significantly responsible for the order imbalance that in turn was one of the conditions that led to the flash crash," CFTC head of enforcement Aitan Goelman told a conference call with journalists.
04/19/2015 Onan, M., A. Salih and B. Yasar Determinants of Implied Volatility Slope of S&P500 Options European Financial Management Association "We document that order flow toxicity measured by Volume Synchronized Probability of Informed Trading (VPIN, Easley et al., 2012) is an important determinant of the slope of the volatility skew besides transactions costs and net buying pressure [...] Model-free risk-neutral skewness measure which is highly correlated with slope is also significantly associated with VPIN."
02/25/2015 Silva, F. and E. Volkova

Can VPIN Forecast Geopolitical Events? An Application to the Crimean Crisis

Cornell University

"We compute the Volume-synchronized Probability of Informed Trading (VPIN) for the Russian main equity index and for individual stocks, finding that for the index level and for most of the stocks it raises considerably between one and three trading days before market prices reflect the invasion [...] Our results provide additional support for the use of VPIN as a measure of monitoring the likelihood of undesirable (geopolitical) events."

01/18/2015 Cheung, W., R. Chou, A. Lei Exchange-Traded Barrier Option and VPIN Journal of Futures Markets "In this study, we provide the first direct evidence of the validity of VPIN outside the US market [...] Our results show that VPIN has significantly incremental predictive power on MCE after controlling for volatility and volume."
12/28/2014 CFA Institute The Volume Clock (Digest Summary) CFA Digest CFA recommended reading.
12/28/2014 CFA Institute Flow Toxicity & Liquidity (Digest Summary) CFA Digest CFA recommended reading.


Panayides, Marios; Shohfi, Thomas; Smith, Jared

Comparing Trade Flow Classification Algorithms in the Electronic Era: The Good, the Bad, and the Uninformative

Proceedings of the Northern Finance Association, 2014

"We find that, despite the use of quote data, Lee and Ready underperforms the other methods, particularly during intervals of high trade and/or quote frequency. The bulk volume algorithm (BVC) demonstrates superiority with respect to data efficiency, accuracy, and the ability to capture informative trade flow."


Michaels, Dave

SEC Finds Misrepresentations by Hedge Funds, Bowden Says

Bloomberg News

Some hedge funds misrepresent their performance in advertising and marketing materials. "SEC examiners also found examples of hedge funds presenting modeled or back-tested performance as actual results and flipping between valuation methodologies, Bowden said." My co-authors and I denounced some of these practices in the May 2014 issue of the Notices of the American Mathematical Society.


Bechler, Kyle; Ludkovski, Michael

Optimal Execution with Dynamic Order Flow Imbalance

University of California, Santa Barbara

Profs. Bechler and Ludkovski examine how VPIN helps achieve optimal execution by adding market microstructure features to the standard transaction cost minimization problem.


Rush, Stephen

Twenty Years of VPIN

University of Connecticut

Prof. Rush implemented VPIN in R, and applied this microstructural theory on a large dataset of stocks. He concludes that VPIN evidences an increased probability of toxicity contagion over the last 20 years.


Barry, M.

Package PBO: Probability of Backtest Overfitting

R/Finance 2014: Applied Finance with R

An implementation of our PBO method in R language.


Song, J, K. Wu and H. Simon

Parameter Analysis of the VPIN (Volume Synchronized Probability of Informed Trading) Metric

Constantin Zopounidis, Editor. Quantitative Financial Risk Management: Theory and Practice. 2014. Wiley.

"VPIN (Volume synchronized Probability of Informed trading) is a leading indicator of liquidity-induced volatility. It is best known for having produced a signal more than hours before the Flash Crash of 2010. On that day, the market saw the biggest one-day point decline in the Dow Jones Industrial Average, which culminated to the market value of $1 trillion disappearing, but only to recover those losses twenty minutes later (Lauricella 2010)."


Haran, B.

π and Four Fingers


Numberphile recently featured my friend, coleague and co-author David H. Bailey. This video explains how David's Spigot algorithm was used in The Simpsons "Marge in Chains" episode.


Yildiz, S., R. Van Ness and B. Van Ness

Analysis of the Determinants of VPIN, HFTs' Order Flow Toxicity and Impact on Stock Price Variance

Univ. Mississippi

"While trade intensity is negatively related to VPIN, return volatility is positively related to VPIN. VPIN has predictive power for future volatility in equity markets, even after controlling for trade intensity. FVPIN contract is a useful hedge tool against toxicity."


Edesess, M. and K.L. Tsui

How Many Monkeys Does it Take to Find a Successful Strategy?

Advisor Perspectives

“We would like to raise the question of whether mathematicians should continue to tolerate the proliferation of investment products that are misleadingly marketed as mathematically founded.”


Russell, K.

Overfitted Backtests

Timely Portfolio

Kenton Russell has published the code in R language that computes the Minimum Backtest Length (MinBTL).


J. MacIntosh

High Frequency Traders: Angels or Devils?

C.D. Howe

Prof. MacIntosh (U. Toronto) cites our work on the Flash Crash in his new study.



High Frequency Trading – An Asset Manager’s Perspective

Norges Bank Investment Management

A good summary of the state of the debate regarding High-Frequency Trading.



Concept Release on Risk Controls and System Safeguards for Automated Trading Environments


The newly published CFTC proposal on Risk Controls cites the VPIN model as a plausible mechanism for preventing flash crashes.


Wu, J. et al.

Testing VPIN on Big Data: Response to "Reflecting on the VPIN dispute"

Lawrence Berkeley National Laboratory

Scientists at Berkeley Lab discuss multiple errors in Torben Andersen and Oleg Bondarenko's study of VPIN.


Wung, C. et al.

Informed Trading and Price Discovery Around the Clock

Journal of Alternative Investments

An analysis of the presence of informed traders in the Eurodollar Futures market, using the VPIN model.


Bailey, D.H., J. M. Borwein, A. Mattingly and G. Wightwick

The computation of previously inaccessible digits of π2 and Catalan's constant

Notices of the American Mathematical Society

My co-author David H. Bailey has recently published an article in AMS' flagship journal in which he reflects on the implications of the celebrated Bailey-Borwein-Plouffe formula for the calculation of π, the standard HPC benchmark.


Zagaglia, P.

PIN: Measuring Asymmetric Information in Financial Markets with R

Universita di Bologna

Prof. Zagaglia has developed a module in R Language to estimate PIN.


Brakke, T.

The Sharpe Edifice

The Research Puzzle

An interesting piece on the state of the discussion regarding Sharpe ratios.


Gollapudi, N. and A. Bose

Current Swap market imbalances and what they mean

Citibank Research

A team of Citibank Researchers find that the BVC algorithm for Bulk Volume Classification signals useful information about Swaps market positioning.


Wei, W., D. Gerace and A. Frino

Informed Trading, Flow Toxicity and the Impact on Intraday Trading Factors

A.A. Business and Finance Journal

This study shows that different capitalization stocks exhibit different VPIN characteristics. It finds that flow toxicity measured through VPIN is able to predict and explain to an extent future quote imbalance, price volatility and volume bucket duration or trade intensity.



A Big Data Approach to Analyzing Market Volatility

Lawrence Berkeley National Laboratory

Berkeley Lab scientists have applied Big Data techniques to complete the largest study ever on volatility. It uses a massive amount of tick data from the one hundred most liquid futures contracts worldwide over a period of five years. They conclude that short-term volatility can be forecasted with false positive rates as low as 7%.


Themis Trading

Front Running – “Strategic Sequential Trading”

Themis Trading

Themis Trading comments on our research on High Frequency Trading and Big Data.


Hunsader, E.

May 6'th 2010 Flash Crash Analysis


NANEX finds several inconsistencies in the CFTC analysis of the Flash Crash. The same study was also criticized by the CME, on similar grounds. The CME and NANEX rarely agree on High-Frequency Trading analyses, as they are on opposite sides of the debate.


Journal of Financial Markets

The Journal of Financial Markets has announced the withdrawal of the paper titled "VPIN and the Flash Crash", written by Torben G. Andersen and Oleg Bondarenko. This paper had been accepted for publication six months earlier, and claimed that "VPIN is a poor predictor of short run volatility".  We had expressed our concerns regarding Andersen and Bondarenko's implementation of VPIN in our paper "VPIN and the Flash Crash: A Comment". Sadly, the withdrawal of this paper has not been given as much publicity as its initial publication [1, 2]. However, withdrawing a paper from an academic journal is an exceptional action, and I commend JFM's editors as well as Andersen and Bondarenko for taking that step. [04/12/2013 UPDATE: Retraction Watch features this retraction in their website (link)]


Menkveld, A. and B. Yueshen

Anatomy of the Flash Crash

VU University Amsterdam; Tinbergen Institute

Menkveld and Yueshen examine VPIN during the flash crash, and show that "the large seller's relative presence in the market co-moves negatively with flow toxicity. This finding is consistent with strategic trading: she sells passively during upturns (her limit sell orders are taken out), sells aggressively right after an upturn, and does not trade in downturns."


Berman, M., V. Krouglov and E. Olin

RAPA Score Triumphs

RAPA Cap Intro

RAPA's whitepaper argues that their PSR-based capital allocation leads to superior fund performance.



Celebrating Pi Day

U.S. Department of Energy

On Pi day, the U.S. Department of Energy paid tribute to the work of Prof. David H. Bailey.


Wolchover, N.

In Computers We Trust?

Simons Foundation

The Simons Foundation asked David H. Bailey to discuss the growing role of Computational Mathematics in Mathematical Research. Best known for the Bailey-Borwein-Plouffe formula, Prof. Bailey is a leading authority in Experimental Mathematics, and has co-authored with Marcos five papers in Mathematical Finance.


Barclay Insider Report

Are hedge funds firing too many managers?


Barclay's Insider Report features our recent paper, "Drawdown-based Stop-Outs and the Triple Penance rule".


R. Wood, J. Upson and H. McInish

The Flash Crash: Trading Aggressiveness, Liquidity Supply, and the Impact of Intermarket Sweep Orders


Consistent with our findings about the Flash Crash, Wood et al. present evidence of  informed trading in the early part of that day, which drove returns over the crash period.


Hwang, L., S. Lim, K. Park and W. Lee

Does information risk affect the implied cost of equity capital? An analysis of PIN and adjusted PIN

Journal of Accounting and Economics

The authors find that estimates of PIN based on Lee-Ready tend to be inaccurate. Using the actual aggressor side information, they obtain PIN estimates that are useful in explaining the ICOE (implied cost of equity capital. This result is consistent with our findings in connection with the Tick Rule, the actual aggressor side, and Bulk Volume Classification (BVC).


Berman, M., V. Krouglov and E. Olin

Release of the new RAPA Ranking Algorithm


Since January of 2013, RAPA CAP Intro will be ranking portfolio managers worldwide following the Probabilistic Sharpe Ratio (PSR) methodology introduced in our paper "The Sharpe Ratio Efficient Frontier".


Klein, L., V. Dalko and M. Wang

Regulating Competition in Stock Markets: Antitrust Measures to Promote Fairness and Transparency through Investor Protection and Crisis Prevention


Lawrence Klein (Nobel Prize, 1980) has teamed up with Harvard professor Viktoria Dalko and RICE's Vice President Michael Wang. The book discusses financial crisis prevention, with references to the VPIN theory.


Corcoran, C.

Systemic Liquidity Risk and Bipolar Markets: Wealth Management in Today's Macro Risk On / Risk Off Financial Environment


Clive Corcoran's new book contains a chapter titled "Detecting mini bubbles with the VPIN metric", in which this author demonstrates how the VPIN theory can be used to monitor the probability of toxicity-induced liquidity crises.


Johnson, T. and E. So

A Simple Multimarket Measure of PIN


Johnson and So propose a new PIN metric that combines information from multiple markets.


Abad, D. and J. Yague

From PIN to VPIN: An Introduction to Order Flow Toxicity

Span Rev Financ Econ

Consistent with a previous study by Lawrence Berkeley National Laboratory, this paper confirms VPIN's forecasting power on stocks' toxicity-induced volatility.


Deutsche Bank Quantitative Strategies

Academic Insights

Deutsche Bank

DB features our new paper: "Balanced Baskets: A new approach to Trading and Hedging Risks".


O'Malia, Scott

“I Have One Word for You: Technology”

U.S. Commodity Futures Trading Commission

CFTC Commissioner O'Malia comments on our recent paper "The Volume Clock: Insights into the High Frequency Paradigm".


Deutsche Bank Quantitative Strategies

Academic Insights

Deutsche Bank

DB features our two newly published paper: "Optimal Execution Horizon" and "The Volume Clock: Insights into the High Frequency Paradigm".


Bethel, W. et al.

Federal Market Information Technology in the Post Flash Crash Era: Roles for Supercomputing

Journal of Trading

In a paper published by the Journal of Trading, a U.S. National Laboratory confirms our results on the "flash crash" and further concludes that "This [VPIN] is the strongest early warning signal known to us at this time."


Deutsche Bank Quantitative Strategies

Academic Insights

Deutsche Bank

Deutsche Bank features the paper "Advanced Cointegration and Subset Correlation Hedging Methods".


UK's Government Office for Science

The Future of Computer Trading in Financial Markets


Maureen O'Hara discusses VPIN in the context of this British Government study.


Carver, Laurie

US regulators ask DOE lab to study flash-crash forecasting tool

Risk Magazine

Risk Magazine reports that U.S. regulators have asked a National Laboratory to study methods to prevent flash-crashes, VPIN being one of the options considered.


Carver, Laurie

OTC flash crash: Dealers consider risks of HFT invasion

Risk Magazine

Risk Magazine features VPIN as a possible way to prevent OTC flash crash.


Deutsche Bank Quantitative Strategies

Academic Insights

Deutsche Bank

This investment bank features "The Sharpe Ratio Efficient Frontier" in their list of selected academic research.


Deutsche Bank Quantitative Strategies

Academic Insights

Deutsche Bank

DB's Global Quantitative Stratregies group discusses the introduction of a new performance measure called "Probabilistic Sharpe Ratio" (PSR), which corrects for the inflationary effects associated with Non-Normal returns.


Deutsche Bank Quantitative Strategies

Academic Insights

Deutsche Bank

This investment bank featured "The Microstructure of the Flash Crash" in their list of selected academic research.


Luo, Yin et al.

Frequency Arbitrage

Deutsche Bank

This Research Note discusses the alpha generated by PIN-style models, and the potential of VPIN for liquidity risk applications.