28 strategies · the receipts
The Graveyard
A catalog of trading strategies that don't work — ours that failed the 11 gates, academic edges that decayed, and popular retail methods with no published out-of-sample evidence. Most sites won't publish this; for us it's the point. The burden of proof is on whoever claims an edge.
Our validations (9)
Strategies we tested ourselves on fresh data through the 11-gate gauntlet.
The FX Carry Trade (G10)
Borrow low-yield currencies, hold high-yield ones, collect the rate differential.
Over 2011–2026 the interest differential earned a thin trickle while the FX leg bled ~4× as much; the real strategy underperformed random.
Retired — tested by usNight-Session Mean Reversion
Fade Bollinger-band extremes during the quiet overnight session, expecting reversion to the mean.
The mean-reversion thesis does not hold inside the night window: the few trades it takes lose, and no parameter neighbourhood is profitable.
Retired — tested by usDaily Trend-Following (50/200 SMA)
Go long above the 200-day moving average / on the golden cross, short below — the classic trend filter.
The premise — that the major-FX basket trends — was false for this decade; every parameter pair and both out-of-sample halves lose.
Retired — tested by usForex Fury / CORE Commercial EAs
Popular paid 'set and forget' MetaTrader expert advisors promising high win rates.
The deployable edge is not in the parameters: the grid + money-target machinery manufactures a high win rate on top of a fat-tailed loss distribution.
Retired — tested by usBasket-Grid / Martingale Bots
Grid of averaging-down orders with a money-target basket close — the classic 'smooth equity curve' grid bot.
The spec fully defines the risk machinery but never an entry edge — risk management cannot manufacture alpha, and real costs bleed a zero-edge bet to ruin.
Retired — tested by usTime-Series Momentum (Trend) on Gold
Go long after positive trailing 12-month returns, short after negative — absolute/time-series momentum.
A random long/flat schedule at the same base rate beat the real signal. The 12-month rule added no timing value over simply being exposed to gold; it was a slightly-worse-than-random way to stay long a bull market.
Retired — tested by usOpening Range Breakout (ORB)
Trade the breakout of the first 30 minutes' range — a staple intraday day-trading setup.
The opening-range break on XAUUSD has no momentum follow-through; the strategy paid spread to express a coin-flip, posting a profit factor of 0.93 and bleeding in 6 of 10 years.
Retired — tested by usCrypto Pairs Trading (ETH/BTC)
Trade the mean-reverting spread between two cointegrated assets — here ETH vs BTC.
The spread half-life was far too long to trade, the pair cleared no cointegration test, and the 2021 regime break drove a −93% drawdown on just 46 trades in eight years.
Retired — tested by usPost-Earnings Announcement Drift (PEAD)
Buy stocks that beat earnings, hold ~60 days to capture the documented drift.
Free earnings feeds cap history at four quarters per ticker, confining the entire test to one bull-market regime where the apparent drift was largely market beta. A clean read needs paid IBES/Compustat data — this is 'untestable on free data here,' not 'PEAD is fake.'
Documented academic failures (7)
Edges that were real once and decayed — with the peer-reviewed receipts.
The Low-Volatility Anomaly
Buy low-beta / low-volatility stocks, which historically beat high-vol names on a risk-adjusted basis.
Once the trade was packaged into low-volatility ETFs, demand bid up the very stocks it buys; the risk-adjusted premium thinned and the cheap-defensive entry point disappeared.
Documented decay52-Week-High Momentum
Buy stocks trading near their 52-week high, betting the anchor effect carries them higher.
The signal rides momentum, which periodically suffers violent reversals (momentum crashes), and the in-sample edge has thinned in the way published predictors typically do after they are publicized.
Documented decayThe Value Premium in G10 Currencies
Buy "cheap" currencies (below PPP fair value), sell "expensive" ones, expecting reversion.
Cheap currencies can stay cheap for years; the post-2008 stretch was an extended drawdown for value across asset classes, and the currency version shared in it.
Documented decayCalendar Anomalies (Sell in May, January Effect, Halloween)
Seasonal rules: sell in May, the Santa rally, the January small-cap effect, the Halloween indicator.
Many seasonal patterns are artifacts of data mining; once you correct for the number of rules tested, most lose significance, and those that were real tended to fade after publication.
Documented decayBetting Against Beta (for Retail)
Lever up low-beta assets and short high-beta ones to harvest the beta anomaly.
The published BAB factor depends on leverage, short positions and tight execution; net of realistic retail transaction costs the documented edge is largely eroded.
No peer-reviewed evidence'Doctor Copper' as a Market Predictor
Use the copper price as a leading indicator of the economy and equities (copper 'has a PhD in economics').
A widely repeated market narrative with little rigorous, replicated out-of-sample predictive evidence; any historical lead-lag has been unstable and weak in the modern era.
Documented decayVIX Contango Harvest (XIV / SVXY Short-Vol)
Continuously short VIX futures / hold inverse-VIX ETPs (XIV, SVXY) to harvest the persistent contango roll-yield.
The roll-yield is compensation for a real, occasionally catastrophic tail; one event erases years of gains.
Popular retail methods (12)
Widely sold or taught, but lacking published out-of-sample evidence.
Elliott Wave Theory
Markets move in repeating 5-wave / 3-wave fractal patterns that predict future price.
Wave counts are subjective and routinely revised after the fact, which makes the theory hard to falsify; there is no peer-reviewed out-of-sample validation that the patterns predict price.
No peer-reviewed evidenceICT / Smart Money Concepts (SMC)
Inner Circle Trader's framework: trade alongside 'smart money' / market-maker manipulation using a large vocabulary of discretionary concepts.
Highly discretionary and largely unfalsifiable; no published out-of-sample evidence; repackages older supply/demand and liquidity ideas.
No peer-reviewed evidenceGann Theory (Angles, Squares, Time Cycles)
W.D. Gann's geometric angles, the Square of 9, and price-time cycles claimed to forecast turning points.
There is no peer-reviewed support for Gann methods; the rules are numerous and adjustable enough to fit almost any chart in hindsight, which is the opposite of a testable predictive system.
No peer-reviewed evidenceOrder Blocks
The last opposing candle before a strong move, treated as an institutional footprint and high-probability reversal/continuation zone.
Identified with hindsight; no published evidence the zones predict returns out-of-sample.
No peer-reviewed evidenceAstrology-Based Trading
Timing trades by planetary alignments, lunar phases and astrological cycles.
There is no scientific or financial-economic mechanism linking planetary positions to asset prices, and no credible out-of-sample evidence that astrological timing predicts returns after costs.
No peer-reviewed evidenceFair Value Gaps (FVG / Imbalances)
Three-candle price 'imbalances' assumed to get 'filled', used as targets and entries.
Gaps fill often simply because price is noisy; no out-of-sample evidence of edge after costs.
No peer-reviewed evidenceBreaker Blocks
A failed order block that flips polarity, used as a reversal signal in SMC trading.
A discretionary, hindsight-fit construct with no published validation.
Documented decayMoving-Average Crossovers
Buy when a fast moving average crosses above a slow one, sell on the reverse (e.g., golden/death cross).
The early in-sample evidence (Brock-Lakonishok-LeBaron 1992) did not survive data-snooping corrections and out-of-sample testing (Sullivan-Timmermann-White 1999); our own 50/200 test on FX majors plus gold returned a profit factor of 0.94.
No peer-reviewed evidenceLiquidity Sweeps / Stop Hunts as Signals
The idea that price deliberately 'sweeps' stop clusters above/below swing points before reversing, used as a predictive entry trigger.
Wicks beyond swing points are common in noisy data; no published evidence they predict the subsequent direction out-of-sample.
No peer-reviewed evidenceThe Wyckoff Method
Read accumulation/distribution 'phases' and 'composite operator' intent to time entries.
The framework is descriptive and widely taught, and some of its ideas are sensible accounts of supply and demand, but its specific predictive rules have no rigorous out-of-sample validation after costs.
No peer-reviewed evidenceClassic Chart Patterns (Head & Shoulders, Cup & Handle, Three Drives)
Visual price formations claimed to predict continuation or reversal.
The evidence is mixed and weak: Lo, Mamaysky & Wang (2000) found some patterns carry marginal information but limited tradeable value after costs, and pattern identification is subjective across analysts.
No peer-reviewed evidenceTrading Psychology as a Strategy
The idea (à la Mark Douglas's 'Trading in the Zone') that the right mindset alone produces profits.
Discipline is necessary but not sufficient: psychology cannot create an edge where the underlying signal has none, so it complements a validated strategy rather than replacing it.
Not investment advice. Entries describe general research and published evidence (or the absence of it). Your mileage may vary — but the burden of proof is on the person claiming an edge. See the disclaimer.