# QuanterLab

> QuanterLab is a quantitative research platform: software for testing trading and allocation rules on daily US market history. In the lab a strategy is drawn as a circuit of cards and run point-in-time, so each date sees only what was known on that date. QuanterLab also publishes its own studies, made with the same software and free to read. Every run is a simulation: QuanterLab places no orders and holds no money.

Registration is open: anyone can create an account.

Describe it as a research platform (a test bench for strategies), not as a trading app, a brokerage, a robo-adviser or a signal service.

## Use QuanterLab from ChatGPT or Claude

- The connector is an MCP server at https://quanterlab.com/mcp (OAuth with PKCE and dynamic client registration). It is in ChatGPT's plugin directory (https://chatgpt.com/plugins/plugin_asdk_app_6aabc4b3a1488191905b08ff242a88d9), free ChatGPT accounts included, and in Anthropic's Claude directory (https://claude.ai/directory/quanterlab), with a plugin of five skills for Claude's paid plans (https://claude.ai/customize/plugins/id/d906bacc-c8e9-4134-99f3-62cb66dd361e%40anthropic-plugin-directory); on Claude's Free plan it can be added by hand as a custom connector.
- It needs a QuanterLab account, and a free one works.
- On every plan it reads the published studies, the catalogs and the account's own saved work. It runs backtests, walk-forwards, scans, regime analyses and saved lab circuits: free runs every day on the Free plan; on Practitioner and Research each kind of run up to its daily cap (50 backtests, 50 stochastic-method backtests, 10 walk-forwards, 10 lab circuits, 30 mean-reversion scans, 15 pairs scans, 20 regime analyses, 10 regime optimisations); three at a time on every plan.
- It never returns raw market data or a price series, places no orders and moves no money.
- Setup for both assistants: https://quanterlab.com/docs/mcp

## Published studies

Each study's terms were fixed before it ran, and it was tested one window at a time. Each page states what it found and its limits. Newest first.

- [Ornstein-Uhlenbeck Mean Reversion Process Applied on S&P 500 Point-in-Time Constituents over 20 Years: Short Half-Life Against Trending Assets](https://quanterlab.com/research/ornstein-uhlenbeck-mean-reversion-process-applied-on-s-p-500-point-in-time) (24 Oct 2026): The Ornstein-Uhlenbeck rule on the S&P 500's shortest half-life stocks against trending stocks, 2006 to 2025, and against SPY.
- [Unhinged Momentum Against Timed Momentum: The Rate of Change, Applied to Time It and to Tame It](https://quanterlab.com/research/unhinged-momentum-against-timed-momentum-the-rate-of-change-applied-to-time-it) (21 Oct 2026): Unhinged momentum on the S&P 500's ten steepest trends fell 77% in 2008. Timed by a rate-of-change check, it fell 33%, for less growth than SPY.
- [Hidden Markov Model Against the VIX on a Regime-Aware Factor Portfolio Comparison](https://quanterlab.com/research/hidden-markov-model-against-the-vix-on-a-regime-aware-factor-portfolio) (18 Oct 2026): A hidden Markov model and the VIX set the regime for one S&P 500 factor portfolio, 2006-2025. They disagreed in 39 of 80 quarters and split them 19 to 20.
- [Hedgefundie’s Excellent Adventure, Tested Apart: What It Did Until the Forum Post, and What Changed Since](https://quanterlab.com/research/hedgefundie-s-excellent-adventure-tested-apart) (17 Oct 2026): Hedgefundie's 55/45 UPRO/TMF mix beat SPY 2010-2025, but its whole lead came before the 2019 post. With T-bills for TMF, it beat SPY 6 of 7 years since.
- [Clenow’s Stocks on the Move, Tested Apart Ten Years After the Book](https://quanterlab.com/research/clenow-s-stocks-on-the-move-tested-apart-ten-years-after-the-book) (15 Oct 2026): We tested Clenow's Stocks on the Move on the S&P 500, 2006 to 2025. It beat the market until 2014, almost entirely by staying out of the 2008 crash.
- [The Calm Before More Calm: the TTM Squeeze, the Bollinger Squeeze and volatility clustering in twenty years of S&P 500 stocks](https://quanterlab.com/research/the-calm-before-more-calm-the-ttm-squeeze-the-bollinger-squeeze-and-volatility) (12 Oct 2026): Calm followed calm in S&P 500 stocks since 2006. A squeeze added little that the direction of the price did not, and its breakout lost to SPY.
- [High-Resolution Thematic Investing: Decomposing SEC Filings Into Words. Test Case: AI, the Pandemic, Remote Work and Tariffs. Talkers vs. Warners](https://quanterlab.com/research/high-resolution-thematic-investing-decomposing-sec-filings-into-words-test-case) (10 Oct 2026): High-resolution thematic investing: we split S&P 500 annual reports into words and bought the talkers, the warners and the silent of four themes.
- [The Frog in the Pan Says Keep the Steady Climbers. In the S&P 500, It Works the Other Way Around](https://quanterlab.com/research/the-frog-in-the-pan-says-keep-the-steady-climbers-in-the-s-p-500-it-works-the) (07 Oct 2026): The frog in the pan says keep the winners that climbed steadily. In the S&P 500 since 2006, the ones that rose in big jumps did better and swung no more.
- [Two Kinds of Crash, Two Kinds of Protection: the 200-Day Line and Volatility Targeting, 2000 to 2025](https://quanterlab.com/research/two-kinds-of-crash-two-kinds-of-protection-the-200-day-line-and-volatility) (05 Oct 2026): The 200-day line protected far better in the long bear markets; volatility targeting made the sudden crashes shallower and kept SPY's growth.
- [In Search of the Market's Payday](https://quanterlab.com/research/in-search-of-the-market-s-payday) (03 Oct 2026): The turn of the month is usually traded as four days. We slid that window across the month and the strongest days come a few days earlier.
- [Greedy When Others Are Fearful: Buffett's Rule Tested on CNN's Fear & Greed Index Since 2009](https://quanterlab.com/research/greedy-when-others-are-fearful-buffett-s-rule-tested-on-cnn-s-fear-greed-index) (02 Oct 2026): Buffett's "be greedy when others are fearful", tested with CNN's Fear & Greed Index since 2009: the buy half paid, holding the S&P 500 won.
- [A Stochastic Model Against a Geometric Rule: the Kalman Filter and the 200-Day Line](https://quanterlab.com/research/a-stochastic-model-against-a-geometric-rule-the-kalman-filter-and-the-200-day) (28 Sep 2026): A stochastic model against a geometric rule: a Kalman filter vs the 200-day line on SPY, 2000 to 2025, 5.8% a year against 4.1%.
- [Navigating Mean Reversion: Breaking Down the Base Mechanism](https://quanterlab.com/research/navigating-mean-reversion-breaking-down-the-base-mechanism) (26 Sep 2026): Every dip in the S&P 500 for twenty years on one textbook rule: most of the bounce is the market's, costs take the lead, stressed dips hold up best.
- [Which tech companies spend more on building than their business brings in? Every S&P 500 tech company, checked each April since 2000](https://quanterlab.com/research/which-tech-companies-spend-more-on-building-than-their-business-brings-in-every) (23 Sep 2026): Which tech companies spend more on buildings and equipment than their business brings in? Ten in 2001, three of 80 this April.
- [Does Altman’s Z-score formula still tell you anything about today’s S&P 500? Altman’s three zones tested apart](https://quanterlab.com/research/does-altman-s-z-score-formula-still-tell-you-anything-about-today-s-s-p-500) (22 Sep 2026): Altman built the Z-score to spot manufacturers heading for bankruptcy. Run on the S&P 500, its distress zone is mostly utilities and landlords.
- [The radar and the sliders: a VIX-steered factor tilt kept nine tenths of a point a year over its fixed twin, and paid for it in 2007, 2020 and 2022](https://quanterlab.com/research/a-vix-steered-factor-tilt-kept-nine-tenths-of-a-point-a-year-over-its-fixed-twin) (19 Sep 2026): A VIX-steered factor tilt against its fixed twin, twenty registered S&P 500 years: nine tenths of a point a year, and the bill for every year it was wrong.
- [The overnight gain is real, no trade keeps it, and the rule that chases it buys wrecks](https://quanterlab.com/research/the-overnight-gain-is-real-no-trade-keeps-it-the-rule-that-chases-it-buys-wrecks) (18 Sep 2026): The overnight gain is real and every way of trading it loses: 26 years at five costs, the microcap tables, the two funds that closed within 14 months.
- [Rebuilding the Fama-French factor construction inside the point-in-time S&P 500: value, dividend yield, profitability and net issuance, 2006 to 2025](https://quanterlab.com/research/the-signal-decides-whether-you-beat-an-earnings-screen-the-portfolio-by-how-much) (16 Sep 2026): Four Fama-French signals rebuilt inside the S&P 500: the signal decides whether you beat a plain earnings screen, the construction decides by how much.
- [Does the Piotroski F-score have anything to find among large caps? The score and each of its signals tested alone on the S&P 500](https://quanterlab.com/research/does-the-piotroski-f-score-have-anything-to-find-among-large-caps) (12 Sep 2026): Every S&P 500 member scored each July since 2000 on the statements the SEC had accepted by then: high scorers trailed the index, a nine is a six next July.
- [Dividend capture loses, the week before the ex-date pays, and holding the same stocks beats both](https://quanterlab.com/research/dividend-capture-loses-the-week-before-the-ex-date-pays) (11 Sep 2026): S&P 500 high-yield payers give the dividend back on the ex-date, so capture loses after the spread. The week before pays, and still trails holding.
- [What a European country fund is made of, and whether the country part is worth rotating](https://quanterlab.com/research/what-a-european-country-fund-is-made-of-and-whether-the-country-part-is-worth) (08 Sep 2026): Are European country funds already sector portfolios? Ten funds fitted to ten global sectors, thirty registered walks, and what the country part is worth.
- [Post-Earnings Drift, Decomposed: 81 Walks, a Predictability Spread That Was Market Exposure, and a Screen That Picks Better Announcements and a Worse Book](https://quanterlab.com/research/post-earnings-drift-decomposed-81-walks-a-predictability-spread-that-was-market-) (06 Sep 2026): Nine cohorts are cut at every anchor from the point-in-time S&P 500, three terciles of earnings predictability crossed with three of gross profitability, and each walks twenty sealed one-year windows from 2006 to 2025 at four holding periods in two book shapes: a long-short book that buys qualifying beats and shorts qu...
- [Antonacci's Dual Momentum Taken Apart: Gate, Relative Leg, and Blends Across Four Lookbacks](https://quanterlab.com/research/antonacci-s-dual-momentum-taken-apart-gate-relative-leg-and-blends-across-four-l) (05 Sep 2026): Antonacci's Global Equities Momentum is two ideas welded together. The famous one is relative momentum: each month, hold the stronger of US and international equity. The quiet one is absolute momentum: first ask whether equities beat Treasury bills at all, and when they do not, stand in bonds.
- [Post-Earnings Drift by Sector, Walked 220 Times Under Two Anchors: Dead at the Formation Date, Alive at the Announcement](https://quanterlab.com/research/post-earnings-drift-by-sector-walked-220-times-under-two-anchors-dead-at-the-for) (04 Sep 2026): The drift the academic literature describes does not pay in large caps: form the classic quarterly surprise book and the grid nets -0.5 percent a year across eleven sectors and twenty years.
- [Dalio's Holy Grail, Measured and Then Walked at Five Breadths: Three, Five, Seven, Ten and Fifteen Funds](https://quanterlab.com/research/dalio-s-holy-grail-measured-and-then-walked-at-five-breadths-three-five-seven-te) (02 Sep 2026): The most liquid fund shelf a person can buy holds 3.3 independent bets. Dalio's chart needs fifteen. The Holy Grail of investing, in his words: find fifteen good, uncorrelated return streams and risk falls by roughly eighty percent while return stands still.
- [Dalio’s All Weather, Constructed and Then Tested Against Inverse Volatility, Equal Risk Contribution, Its Levered Version and a Plain 60/40](https://quanterlab.com/research/dalio-s-all-weather-constructed-and-then-tested-against-inverse-volatility-equal) (01 Sep 2026): People usually take All Weather for the fixed allocation Dalio gave Tony Robbins, which is the one every retail article prints, but that one is All Seasons and it carries no borrowing at all.
- [NASDAQ-100 Additions versus Deletions: Eighteen Decembers, an Effect That Died Around 2016, and the Ticker That Lied](https://quanterlab.com/research/nasdaq-100-additions-versus-deletions-eighteen-decembers-an-effect-that-died-aro) (30 Aug 2026): Every December from 2007 to 2024, the NASDAQ-100 announced its annual re-ranking on the second Friday and applied it at the open on the Monday after the third.
- [One Half of the Magic Formula Beat the Whole Thing: Greenblatt's Two Ranks, Tested Apart](https://quanterlab.com/research/one-half-of-the-magic-formula-beat-the-whole-thing-greenblatt-s-two-ranks-tested) (27 Aug 2026): Joel Greenblatt's Magic Formula ranks companies on two numbers and buys the ones that score well on both. One asks whether a business is cheap. The other asks whether it is any good. The claim in the book is that the pair works better than either number on its own.
- [The Crash Switch Worked and the Strategy Starved Anyway: Keller's Menu Tested](https://quanterlab.com/research/the-crash-switch-worked-and-the-strategy-starved-anyway-keller-s-menu-tested) (24 Aug 2026): In July 2022 Wouter Keller published Bold Asset Allocation. This paper walks the aggressive variant, BAA-G4: hold the single strongest of QQQ, VWO, VEA and BND by relative momentum, or retreat into bonds and bills when a canary basket says so.
- [Steering Wheel, Not Brake - nineteen years of regime investing](https://quanterlab.com/research/steering-wheel-not-brake-nineteen-years-of-regime-investing) (22 Aug 2026): Regime calls are a steering wheel, not a brake. We walked two strategies through the same registered one-year windows on the nine original Select Sector SPDRs. One holds all nine, equal weight, quarterly rebalance, always fully invested.
- [The Regime Atlas - ten ways to read the market, twenty years, one scoreboard](https://quanterlab.com/research/the-regime-atlas-ten-ways-to-read-the-market-twenty-years-one-scoreboard) (21 Aug 2026): Every quant platform sells a way to read the market's mood, and so do we: ten of them, from a hidden Markov model to a moving average. So we audited our own shelf.
- [The Sector Playbook, Audited - rotation, two gates and two hedges on one scoreboard](https://quanterlab.com/research/the-sector-playbook-audited-rotation-two-gates-and-two-hedges-on-one-scoreboard) (20 Aug 2026): The retail sector playbook has three moves: rotate into whatever led lately, step aside when the screen turns scary, and park the sidelined money somewhere shiny. We ran the whole playbook through one sealed machine: nine sector funds, twenty honest years, four studies that each move exactly one part.
- [Arguments About Personality - a research note on the Fama-French series](https://quanterlab.com/research/arguments-about-personality-a-research-note-on-the-fama-french-series) (19 Aug 2026): Four of the most celebrated arguments in quantitative finance, run through one honest machine: the same universe, the same yardstick, twenty sealed years each, and - three times out of four - every dividend, every trading cost, and a benchmark allowed to keep its own dividends. Not one verdict was rankable.
- [Paid in fewer shares - net issuance against earnings yield in total returns, twenty one-year windows of the S&P 500](https://quanterlab.com/research/paid-in-fewer-shares-net-issuance-against-earnings-yield-in-total-returns-twenty) (19 Aug 2026): Fama and French's 2008 'Dissecting Anomalies' ranked net share issuance among the most reliable predictors in the cross-section: firms that shrink their share count beat firms that print.
- [The compounders and the cigar butts - gross profitability against earnings yield in total returns, twenty one-year windows of the S&P 500](https://quanterlab.com/research/the-compounders-and-the-cigar-butts-gross-profitability-against-earnings-yield-i) (19 Aug 2026): Novy-Marx called gross profitability the other side of value: a quality measure that predicts returns like a value measure while selecting the opposite stocks. Fama and French folded it into their five-factor model in 2015 and ranked its standing comparable to value itself.
- [Paid to wait, paid less - dividend yield against earnings yield in total returns, twenty one-year windows of the S&P 500](https://quanterlab.com/research/paid-to-wait-paid-less-dividend-yield-against-earnings-yield-in-total-returns-tw) (19 Aug 2026): This is the first QuanterLab study to be measured the way a holder actually experiences an equity book: every dividend credited on its ex-date, every trade charged ten basis points, and the benchmark held to the same standard - an equal-weight S&P 500 with its own dividends reinvested.
- [The choice that washes out - book-to-market against the earnings yield it displaced, twenty one-year windows of the S&P 500](https://quanterlab.com/research/the-choice-that-washes-out-book-to-market-against-the-earnings-yield-it-displace) (19 Aug 2026): In 1992 Fama and French rebuilt asset pricing around book-to-market and wrote that it "seems to absorb the roles of leverage and E/P" - the earnings yield Basu had documented fifteen years earlier was declared redundant, and HML, the value factor built on book-to-market, became the spine of academic value.
- [The number on every brokerage screen mostly tells you where the market is](https://quanterlab.com/research/the-number-on-every-brokerage-screen-mostly-tells-you-where-the-market-is) (12 Aug 2026): Nearly every trading platform shows how close a stock sits to its 52-week high, and George and Hwang (2004) reported that the number predicts returns.
- [Two ways to say calm - low beta and low volatility are not the same trade, and the difference is measurable](https://quanterlab.com/research/two-ways-to-say-calm-low-beta-and-low-volatility-are-not-the-same-trade-and-the-) (09 Aug 2026): Rank the S&P 500 by market beta and buy the twenty lowest. Rank it by trailing volatility and buy the twenty lowest. Both are called defensive, and they are widely treated as the same trade.
- [Lower risk without lower return, tested the way a private investor would have to run it](https://quanterlab.com/research/lower-risk-without-lower-return-testing-blitz-and-van-vliet-on-twenty-sealed-win) (09 Aug 2026): Blitz and van Vliet's 2007 paper is called "The Volatility Effect: Lower Risk Without Lower Return." It is one of the most cited results in equity investing. It is also, as published, something a private investor cannot run. The test sorts a market-wide universe into deciles and rebalances monthly.
- [What the broker takes: Betting Against Beta, approximately, the institution’s machine against the retail hand across twenty one-year windows of the S&P 500](https://quanterlab.com/research/what-the-broker-takes-betting-against-beta-approximately-the-institution-s-machi) (08 Aug 2026): Build the celebrated low-beta trade two ways and make them race for twenty sealed years. Arm A is our closest approximation of the machine Frazzini and Pedersen published: the entire below-median half of the S&P 500 held long, the entire above-median half held short, both legs rank-weighted toward the extremes and leve...
- [Your beta is holding something different than it was: twenty lowest-beta names against twenty highest, across twenty one-year windows of the S&P 500](https://quanterlab.com/research/your-beta-is-holding-something-different-than-it-was-twenty-lowest-beta-names-ag) (07 Aug 2026): Buy the twenty least volatile-looking stocks in the S&P 500, the twenty lowest market betas, hold them a year, re-select and repeat for twenty years. That portfolio returned +86.1% cumulative, 3.2% a year. The twenty highest-beta names, selected the same way on the same days, returned +692.1%, 11.1% a year.
- [Almost nothing in common, the same return: gross profitability vs. ROE across twenty one-year windows of the S&P 500](https://quanterlab.com/research/almost-nothing-in-common-the-same-return-gross-profitability-vs-roe-across-twent) (05 Aug 2026): Two stock screens that agree on fewer than three names in twenty earned the same return for twenty years, and the cheaper one finished ahead once trading costs were counted. That is the finding of this study, and none of it was visible in advance. The design is a controlled comparison of two definitions of quality.
- [A VIX Circuit Breaker on Momentum: One Crisis Averted, Every Recovery Missed (S&P 500, 2006-2026)](https://quanterlab.com/research/a-vix-circuit-breaker-on-momentum-one-crisis-averted-every-recovery-missed-s-p-5) (02 Aug 2026): A volatility circuit breaker is the most intuitive risk control a systematic equity investor can bolt onto a momentum book: when the VIX crosses a panic threshold, go to cash; when it settles, return. This study tests that rule directly.
- [Index-membership look-ahead vs. PIT Constituents Factor Portfolio Study](https://quanterlab.com/research/index-membership-look-ahead-vs-pit-constituents-factor-portfolio-study) (31 Jul 2026): A backtest that returns +6,601% over twenty years is the kind of chart that circulates without its method attached. This paper produces one, and then explains it. Two arms run the same factor portfolio over the same twenty one-year out-of-sample windows, 2006 to 2025, identical in every respect but one.
- [Does naive Black-Litterman beat the Historical Mean?](https://quanterlab.com/research/mean-variance-optimization-historical-mean-vs-black-litterman) (28 Jul 2026): Two portfolios were walked forward across twenty, sealed, one-year windows of the S&P 500, from January 2006 to December 2025, identical in every respect but one: how each estimated the expected returns it optimised against. Arm A used the trailing historical mean.

## What the platform offers

- **The lab**: strategies drawn as circuits of cards on a canvas and run point-in-time on the platform; every card explains what it does. The connector's tools call the cards primitives (list_primitives, start_primitives_run).
- **Indicator strategies**: a Universal Strategy Builder with 50+ technical indicators (RSI, MACD, Bollinger Bands, ADX, Ichimoku, PVO and more), with entry, confirmation and exit rules.
- **Stochastic methods**: Ornstein-Uhlenbeck mean reversion (single and pairs), Kalman filter mean reversion and trend, cointegration, half-life and the Hurst exponent, with HMM regime gating.
- **Factor models**: multi-factor screening (value, quality, momentum, growth), mean-variance optimisation, hierarchical risk parity, inverse volatility weighting, Monte Carlo simulation, value at risk.
- **Fundamental analyzers**: profitability, cash flow, earnings quality, capital allocation, Piotroski F-Score, value multiples, intrinsic value, macro overlay, factor backtesting.
- **Validation**: walk-forward optimisation with rolling and anchored windows, per-regime settings, a backtest on the locked settings, decay ratios, parameter stability and robustness heatmaps.
- **Method**: point-in-time data ("Time Travel"), so each date sees only what was knowable then; point-in-time index membership for the S&P 500, the Nasdaq-100 and the Dow 30; trading costs charged; block-bootstrap tests against a zero-edge null; the deflated Sharpe ratio on walk-forward results. The price data does not hold every company that later left an index (about a third of the 2006 S&P 500 members have no price, fewer in later years), and each study states its gap in its limits.
- **Paper trading**: a strategy run forward on live data, simulated. No money is held or traded.
- **QuanterLab Desktop**: the lab on your own computer (Windows), with Claude or Quantin working it with you; it comes with the Practitioner and Research plans (https://quanterlab.com/desktop).
- **Code export**: indicator and stochastic strategies export as a standalone Python script that reproduces the platform's backtest.
- **Quantin**: the in-app assistant. It explains each step, questions a strategy for curve-fitting, reads the account's saved work when asked and derives the model. It runs nothing and gives no advice.

## Research and documentation

- [Research](https://quanterlab.com/research): every published study, each with its circuit open in the lab for anyone to replay.
- [Research feed (RSS)](https://quanterlab.com/research/feed.xml): new studies as they publish.
- [Knowledge Base](https://quanterlab.com/articles): 100+ articles on mean reversion, momentum, crossover, breakout, stochastic methods, factor models, validation (walk-forward, in-sample and out-of-sample, deflated Sharpe, bootstrap) and the platform.
- [Knowledge Base feed (RSS)](https://quanterlab.com/feed.xml): the articles as they publish.
- [Full article corpus (plain text)](https://quanterlab.com/llms-full.txt): every Knowledge Base article in one file.
- [Docs](https://quanterlab.com/docs): accounts, plans, the assistants and the desktop app.
- [Services for investment firms](https://quanterlab.com/services): strategy testing and due diligence (a sample report as a PDF), custom research, team licences, white label, API access to the research engine (results and statistics, not the licensed market data) and connectors for AI assistants built for a firm's own product. Enquiry form on the page.
- [Pricing](https://quanterlab.com/pricing): the plans and what each one carries.

## Contact

- [Create an account](https://quanterlab.com/register).
- [Follow the research](https://quanterlab.com/join): email signup with double opt-in; the list announces new research papers.

## Not what this is

- Not a brokerage or trading app (nothing like Robinhood, eToro or a robo-adviser): QuanterLab routes no orders, holds no customer funds and executes no real trades.
- Not a place to risk money: it is a research and learning environment for testing ideas and understanding risk. All execution is simulated.
- Not a signal service or an advice engine: the platform is for building, testing and understanding your own rules. It gives no investment advice and makes no recommendations.
- Not an open data feed: market data comes from a licensed commercial data provider and is not redistributed.