Quantitative finance · research notes · how funds work
A strategy only counts once it works on data it has never seen.
Out of Sample is an independent publication about systematic investing. We explain the research behind momentum and factor strategies, the machine-learning methods that have entered finance, the tools used to test ideas honestly, and the institutions that surround a hedge fund, from the prime broker to the auditor. Every article links to the papers, regulators and documentation it relies on.
Education, not advice. Nothing on this site is a recommendation to buy or sell anything. Backtests describe the past under assumptions; real trading adds costs, slippage and risks they leave out.
Where to start
Six pieces that set out the ground the rest of the site builds on.
- Momentum strategies: what the evidence on winners and losers actually says, from 1993 to today.
- Building an automated trading system: the parts of a pipeline and where they fail.
- A laboratory for machine learning in finance: bars, labels and validation done carefully.
- Value at risk: three ways to compute it and why regulators moved beyond it.
- Prime brokers: leverage, securities lending and the lesson of 2008.
- Open source for quantitative finance: languages, libraries and data.
Topics
- Systematic tradingHow rule-based trading systems are designed, tested, automated and run, from a spreadsheet crossover to fully automated execution.
- Momentum & factorsCross-sectional and time-series momentum, dual momentum, momentum crashes and the factor models used to explain returns.
- Financial machine learningLabelling, meta-labelling, fractional differentiation and the research tools that grew up around machine learning for markets.
- Risk & portfoliosValue at risk, volatility targeting, regime models and how diversified strategies are combined into a portfolio.
- Inside a hedge fundPrime brokers, custodians, auditors, seed capital and the investors and contracts that surround a fund.
- Open researchOpen-source tools for quantitative finance and the idea of researching a systematic fund in public.
Recently published
- Bridging the gap into hedge funds: roles, skills and routes in
A practical guide for students and career changers who want to work at a hedge fund: the main roles from quantitative researcher to operations, the skills each needs, education routes, how interviews typically work, building a credible research portfolio, and realistic expectations.
- Accredited investors and qualified purchasers: who may invest in a hedge fund
Why access to hedge funds is restricted, the U.S. accredited investor definition under Regulation D including the 2020 amendments, qualified purchasers and qualified clients, how status is verified, and the equivalent concepts of professional and well-informed investors in Europe and the UK.
- Clawback clauses: taking back pay and profits that were not really earned
What clawback clauses are in finance: general partner clawbacks in private equity, why hedge funds use high-water marks instead, deferred bonuses and malus at banks, Sarbanes-Oxley section 304, Dodd-Frank section 954 and SEC Rule 10D-1, and the practical limits of recovering money already paid.
- Seed capital for hedge funds: how seeding deals work
What seed capital means for a new hedge fund manager: why first money is so hard to raise, who provides seed and acceleration capital, the typical economic terms such as revenue shares, lock-ups and capacity rights, governance and transparency conditions, and the trade-offs for both sides.
- Dreaming, thinking machines: from automata to algorithms in the markets
An essay on the long history of the idea of thinking machines, from mechanical automata and Descartes to Turing's imitation game, ELIZA, the Chinese room and modern machine learning, and what that history suggests about the limits of algorithms in financial markets.
- mlfinlab on the PyPI index: packaging financial research code, and what happened next
How a Python research library reaches users through the Python Package Index, what versioning, licences and tests mean for reproducible quantitative research, and the story of mlfinlab, which moved from an open-source licence to a commercial one.
- Family offices: how wealthy families manage money, and why they matter to hedge funds
What single-family and multi-family offices are, what services they provide beyond investing, how they allocate to hedge funds and direct investments, their regulatory treatment including the SEC family office rule, and the questions raised by the Archegos collapse.
- Advances in Financial Machine Learning: a map of the techniques and the tools that implement them
A chapter-by-chapter map of Marcos López de Prado's Advances in Financial Machine Learning, from financial data structures to backtest statistics and hierarchical risk parity, with notes on which ideas are most used and how open-source implementations evolved.
- Fractional differentiation: stationary features that keep their memory
Why the usual choice between prices and returns forces a trade-off between stationarity and memory, how fractional differencing with a non-integer order works, the binomial weights, the fixed-window method, choosing d with an ADF test, and pitfalls.
- Asset custodians: who actually holds a fund's securities
What custodian banks do for investment funds: safekeeping, settlement, asset servicing and reporting, the chain from central securities depositories to sub-custodians, segregation of client assets, the SEC custody rule, AIFMD depositaries and how custody differs from prime brokerage.
