Trend fresh_52w_high_low

Fresh 52-Week High / Low (with cooldown)

Fires only on the FIRST day a stock breaks to a new 52-week high or low, then suppresses for `cooldown` trading days before triggering again. Unlike '52-Week New High/Low' which fires every day the condition holds, this avoids flooding screens when a stock trends through a breakout for weeks. Bullish: first fresh high break. Bearish: first fresh low break.

Signal family

Trend — Signals that fire when price is continuing or reversing an established directional move. Momentum-following by nature.

Parameters

Name Description Default Range
period Lookback period (days) 252 126–504
cooldown Cooldown period (trading days) 20 0–120

Historical context

442,944 triggers on 21,144 tickers, 1989-02-15 → 2026-05-01. Universe: global — all covered exchanges (mcap ≥ $100,000,000, price ≥ $1). Long-only convention: BUY at open T+1, hold the horizon, compare to S&P 500 Equal Weight over the same window.

Methodology footnotes

Benchmarks shown in the detail tables: spxew (S&P 500 Equal Weight — primary, median-stock view, avoids the 2020+ megacap-concentration distortion), spx (S&P 500 cap-weighted, distorted post-2020), msci (MSCI World USD). Per-stock regime tags: trending = ADX(14) ≥ 25, high vol = 20d realized annualized vol ≥ 20%. 1d return = intraday T+1 open→close; 20d = open T+1 to close T+20.

At a glance — alpha vs S&P 500 Equal Weight, global universe

Holding-period sensitivity. Bullish columns: positive = signal worked (long the trigger beat the index). Bearish columns: negative = signal worked (the flagged stock underperformed).

Horizon Bullish α Bearish α
5-day +0.08% -0.14%
20-day +0.56% -0.12%
60-day +1.54% -0.14%
1-year +5.87% +1.14%
Random-date null check (20-day): Bullish: beats random (p=0.005).
Bearish: worse than random (p=0.995).

Where does FRESH_52W_HIGH_LOW actually fire?

The bucket distribution often reveals what the signal really is, regardless of its textbook label. Heavy concentration in "non-trending + high vol" = it's mostly a chop-market event. Heavy in "trending + low vol" = it picks up the smooth grinds. Read the chart before the alpha numbers — context shapes everything that follows.

Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — trigger count distribution by per-stock regime quadrant (trending/non-trending × high/low realized volatility) for bullish and bearish triggers, global universe — bullish half — measured on fresh_52w_high
Bullish half — measured on fresh_52w_high
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — trigger count distribution by per-stock regime quadrant (trending/non-trending × high/low realized volatility) for bullish and bearish triggers, global universe — bearish half — measured on fresh_52w_low
Bearish half — measured on fresh_52w_low

Does it work in every regime?

Trigger alpha split by the host stock's own regime on the trigger date — trending or ranging, high-vol or low-vol. This is the 20-day alpha a trade taken on the trigger would have captured. Bars carrying the sign that favours the trade (positive for bullish triggers, negative for bearish) mark the regimes where the signal worked; the opposite sign marks regimes to avoid. One strong bar beside three flat ones is not a "20-day alpha" signal — it is a "20-day alpha when the stock is X" signal. Bar labels carry the sample size; a cell built on a handful of triggers is noise, not a regime finding.

Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — mean 20-day alpha versus S&P 500 Equal Weight by per-stock regime quadrant, bullish and bearish triggers side by side — bullish half — measured on fresh_52w_high
Bullish half — measured on fresh_52w_high
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — mean 20-day alpha versus S&P 500 Equal Weight by per-stock regime quadrant, bullish and bearish triggers side by side — bearish half — measured on fresh_52w_low
Bearish half — measured on fresh_52w_low
Trending + Low vol
Stock in a clean directional move with low realized volatility. Textbook "trend-following paradise" — smooth grind with little whipsaw risk.
Trending + High vol
Violent directional moves — parabolic rallies, crisis selloffs. Trend exists but the path is noisy. Signal timing may be imprecise.
Non-trending + Low vol
Quiet chop, summer doldrums, consolidations. No directional bias but also no big swings — small edges become reliable if they exist at all.
Non-trending + High vol
Choppy and violent — the classical "whipsaw zone" for momentum signals. Crossovers and breakouts fire repeatedly without follow-through.

Does it work in every era?

A multi-year average can hide major instability. The sample splits into three windows: 2015–2019 (pre-COVID), 2020–2022 (pandemic + 2022 bear), and 2023+ (post-ZIRP + AI megacap rally). All three carrying the sign that favours the trade means the signal is durable; one era doing all the work means a regime-specific edge that may not repeat. The greater the variance across eras, the smaller the position it justifies. Long-history signal: requires 260 trading days of prior data per ticker. The earliest era may show fewer triggers as a result.

Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — 20-day alpha split by historical sub-period (2015-2019, 2020-2022, 2023+) to check consistency across market regimes — bullish half — measured on fresh_52w_high
Bullish half — measured on fresh_52w_high
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — 20-day alpha split by historical sub-period (2015-2019, 2020-2022, 2023+) to check consistency across market regimes — bearish half — measured on fresh_52w_low
Bearish half — measured on fresh_52w_low

Longer-horizon views

This signal carries a long lookback window (260 trading days of prior history required per ticker), suggesting it's designed to catch moves that play out over months, not days. The charts below repeat the quadrant and sub-period analyses at the 60-day and 1-year (252-day) horizons, showing how the signal's relationship with the benchmark evolves with holding period.

60-day alpha by stock regime

Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — mean 60-day alpha versus S&P 500 Equal Weight by per-stock regime quadrant — bullish half — measured on fresh_52w_high
Bullish half — measured on fresh_52w_high
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — mean 60-day alpha versus S&P 500 Equal Weight by per-stock regime quadrant — bearish half — measured on fresh_52w_low
Bearish half — measured on fresh_52w_low

60-day alpha by era

Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — 60-day alpha split by historical sub-period — bullish half — measured on fresh_52w_high
Bullish half — measured on fresh_52w_high
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — 60-day alpha split by historical sub-period — bearish half — measured on fresh_52w_low
Bearish half — measured on fresh_52w_low

1-year alpha by stock regime

Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — mean 1-year (252 trading day) alpha versus S&P 500 Equal Weight by per-stock regime quadrant — bullish half — measured on fresh_52w_high
Bullish half — measured on fresh_52w_high
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — mean 1-year (252 trading day) alpha versus S&P 500 Equal Weight by per-stock regime quadrant — bearish half — measured on fresh_52w_low
Bearish half — measured on fresh_52w_low

1-year alpha by era

Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — 1-year alpha split by historical sub-period — bullish half — measured on fresh_52w_high
Bullish half — measured on fresh_52w_high
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — 1-year alpha split by historical sub-period — bearish half — measured on fresh_52w_low
Bearish half — measured on fresh_52w_low

1-year observed lift vs random-date null — bullish side

Observed 1-year lift (vertical line) against the null distribution of random-date firing. If the line is deep inside the null cloud, the signal adds no information. If it sits in the right tail, the signal is doing real work in that direction; in the left tail it ran inverted — random dates served the bullish case better than its own triggers did.
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — bullish 1-year observed lift versus the random-date permutation null distribution

1-year observed lift vs random-date null — bearish side

Observed 1-year lift (vertical line) against the null distribution of random-date firing. If the line is deep inside the null cloud, the signal adds no information. If it sits in the left tail, the signal is doing real work in that direction; in the right tail it ran inverted — random dates served the bearish case better than its own triggers did.
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — bearish 1-year observed lift versus the random-date permutation null distribution

↑ Bullish triggers

Bench Metric 1d 5d 20d 60d 252d
spxew Stock % -0.01% +0.26% +1.15% +3.58% +14.85%
Bench % +0.04% +0.18% +0.66% +2.04% +8.96%
Alpha % -0.05% +0.08% +0.56% +1.54% +5.87%
Median alpha -0.11% -0.24% -0.61% -1.25% -4.27%
Hit rate (α>0) 47.4% 47.6% 47.0% 46.7% 44.6%
p (naive) <0.001 <0.001 <0.001 <0.001 <0.001
p (HAC) <0.001 <0.001 <0.001 <0.001 <0.001
N 242,682 233,816 232,425 224,568 191,636
spx Stock % -0.01% +0.26% +1.15% +3.58% +14.85%
Bench % +0.02% +0.20% +0.89% +2.87% +12.57%
Alpha % -0.03% +0.06% +0.31% +0.70% +2.12%
Median alpha -0.10% -0.29% -0.91% -2.17% -8.09%
Hit rate (α>0) 47.5% 47.1% 45.6% 44.2% 40.1%
p (naive) <0.001 <0.001 <0.001 <0.001 <0.001
p (HAC) <0.001 <0.001 <0.001 <0.001 <0.001
N 244,726 236,759 234,530 227,566 194,085
msci Stock % -0.01% +0.26% +1.15% +3.58% +14.85%
Bench % +0.04% +0.18% +0.73% +2.36% +9.68%
Alpha % -0.05% +0.07% +0.47% +1.22% +4.95%
Median alpha -0.13% -0.28% -0.74% -1.62% -5.17%
Hit rate (α>0) 46.8% 47.2% 46.4% 45.5% 43.6%
p (naive) <0.001 <0.001 <0.001 <0.001 <0.001
p (HAC) <0.001 <0.001 <0.001 <0.001 <0.001
N 242,963 234,989 233,688 225,225 192,860
Observed 20-day lift (vertical line) against the null distribution of random-date firing. If the line is deep inside the null cloud, the signal adds no information. If it sits in the right tail, the signal is doing real work in that direction; in the left tail it ran inverted — random dates served the bullish case better than its own triggers did.
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — bullish 20-day observed lift versus random-date permutation null (200 iterations)
Permutation null detail — all horizons × each benchmark
200-iteration null: for each ticker, sample N random dates from its history (matching observed trigger count) and compute the same alpha. Both observed and null are baseline-centered per ticker (each ticker's own baseline alpha is subtracted), which removes the universe-selection lift that all surviving names share, so the comparison is about the trigger's timing. It does not put the null at zero: that baseline is a median, while a random date's expectation is the ticker's mean, so the null settles at the gap between the two — the right-skew of the ticker's own alpha distribution, positive for equities. Read observed minus null, not the absolute position of either column — which is also why these figures do not match the α columns in the tables above (those are raw, uncentered means). pperm = one-sided fraction of null iters with mean in the "signal was right" tail (right for bullish, left for bearish), so it runs from a floor of 0.005 (trigger dates beat every random draw in the claimed direction) to a 1.000 ceiling (every random draw served the claimed direction better — a reliably inverted signal, not an absent one). The floor is 1/(iterations + 1) and moves with the iteration count; the ceiling does not. Either end says the result was reliable, not that it was large: the gap between the line and the cloud can be a fraction of a percent and still reach an endpoint, and the transaction-cost floor in the caveats below would swallow a gap that small. Read the size off the α and hit-rate columns, the reliability off pperm.
Horizon Bench Observed lift Null mean Null 95% CI pperm
1d spxew +0.08% +0.07% [+0.06%, +0.08%] 0.005
1d spx +0.09% +0.08% [+0.07%, +0.09%] 0.060
1d msci +0.09% +0.08% [+0.07%, +0.09%] 0.134
5d spxew +0.40% +0.31% [+0.29%, +0.34%] 0.005
5d spx +0.43% +0.33% [+0.30%, +0.35%] 0.005
5d msci +0.43% +0.33% [+0.31%, +0.36%] 0.005
20d spxew +1.22% +1.02% [+0.97%, +1.07%] 0.005
20d spx +1.21% +1.06% [+1.01%, +1.10%] 0.005
20d msci +1.25% +1.07% [+1.02%, +1.11%] 0.005
60d spxew +2.27% +2.25% [+2.17%, +2.35%] 0.279
60d spx +2.19% +2.33% [+2.25%, +2.41%] 1.000
60d msci +2.25% +2.33% [+2.25%, +2.42%] 0.970
252d spxew +1.90% +3.99% [+3.80%, +4.21%] 1.000
252d spx +2.27% +4.37% [+4.17%, +4.58%] 1.000
252d msci +2.61% +4.28% [+4.08%, +4.49%] 1.000

Example triggers on US large-caps (2023+, mcap ≥ $30B)

Six recent bullish FRESH_52W_HIGH_LOW triggers on US mega-caps, ranked within this sample of six: the top three and the bottom three, with extreme outliers excluded. Ranking is relative, not absolute — where the signal did well across the sampled names, even the bottom three can have beaten the benchmark, so the alpha printed on each panel is what settles it. Both groups are tail outcomes by construction; read them as the range, not the typical result.

Best three of the six sampled
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — strongest bullish trigger #1 on a US mega-cap, showing the stock's OHLC candles, moving averages, signal-specific overlays, and the 20-day forward window Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — strongest bullish trigger #2 on a US mega-cap, showing the stock's OHLC candles, moving averages, signal-specific overlays, and the 20-day forward window Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — strongest bullish trigger #3 on a US mega-cap, showing the stock's OHLC candles, moving averages, signal-specific overlays, and the 20-day forward window
Weakest three of the six sampled — not necessarily losses
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — weakest bullish trigger #1 on a US mega-cap, showing the 20-day forward window where the signal failed Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — weakest bullish trigger #2 on a US mega-cap, showing the 20-day forward window where the signal failed Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — weakest bullish trigger #3 on a US mega-cap, showing the 20-day forward window where the signal failed
Stock-regime quadrants (2×2 per-stock, 20d alpha detail table)
Each quadrant groups triggers by the stock's own ADX(14) and RV(20) at the trigger date — the textbook conditioning variable (not market-level). Stock %, bench %, alpha %, and HAC p-value shown for each benchmark.
Quadrant N Stock % (spxew) Bench % (spxew) Alpha % (spxew) p (HAC) Stock % (spx) Bench % (spx) Alpha % (spx) p (HAC) Stock % (msci) Bench % (msci) Alpha % (msci) p (HAC)
Trending + Low vol Clean directional grind, low whipsaw 26,304 +0.79% +0.29% +0.54% <0.001 +0.79% +0.67% +0.14% 0.0019 +0.79% +0.48% +0.34% <0.001
Trending + High vol Crisis selloff or parabolic rally 118,686 +1.26% +0.68% +0.66% <0.001 +1.26% +0.91% +0.40% <0.001 +1.26% +0.76% +0.56% <0.001
Non-trending + Low vol Quiet chop, summer doldrums 24,471 +0.71% +0.38% +0.38% <0.001 +0.71% +0.68% +0.04% 0.2890 +0.71% +0.49% +0.25% <0.001
Non-trending + High vol Classical "whipsaw zone" for momentum 81,276 +1.39% +0.84% +0.61% <0.001 +1.39% +0.98% +0.46% <0.001 +1.39% +0.83% +0.61% <0.001
Sub-period breakdown table (20d alpha)
Historical clustering check. If alpha concentrates in one era, the signal's robustness is questionable.
Period N Alpha % (spxew) p (HAC) Alpha % (spx) p (HAC) Alpha % (msci) p (HAC)
2015-2019 2015-01-01 → 2020-01-01 60,537 +0.06% 0.1803 -0.28% <0.001 -0.07% 0.0990
2020-2022 2020-01-01 → 2023-01-01 76,419 +0.51% <0.001 +0.70% <0.001 +0.91% <0.001
2023-2026 2023-01-01 → 2099-01-01 115,094 +0.88% <0.001 +0.39% <0.001 +0.49% <0.001

↓ Bearish triggers negative alpha = signal was right (stock underperformed market)

Bench Metric 1d 5d 20d 60d 252d
spxew Stock % -0.09% -0.21% +0.88% +2.88% +12.48%
Bench % +0.00% -0.09% +0.94% +3.01% +11.39%
Alpha % -0.09% -0.14% -0.12% -0.14% +1.14%
Median alpha -0.08% -0.27% -0.87% -2.10% -7.77%
Hit rate (α>0) 48.3% 47.6% 46.0% 44.6% 40.6%
p (naive) <0.001 <0.001 <0.001 0.0059 <0.001
p (HAC) <0.001 <0.001 <0.001 0.0227 <0.001
N 184,330 177,844 175,834 172,560 164,517
spx Stock % -0.09% -0.21% +0.88% +2.88% +12.48%
Bench % -0.02% +0.07% +1.31% +3.50% +15.34%
Alpha % -0.07% -0.26% -0.41% -0.61% -2.63%
Median alpha -0.07% -0.35% -1.13% -2.59% -11.78%
Hit rate (α>0) 48.6% 46.8% 44.9% 43.6% 36.6%
p (naive) <0.001 <0.001 <0.001 <0.001 <0.001
p (HAC) <0.001 <0.001 <0.001 <0.001 <0.001
N 186,266 179,958 178,734 175,187 167,195
msci Stock % -0.09% -0.21% +0.88% +2.88% +12.48%
Bench % +0.03% +0.04% +1.15% +3.19% +13.12%
Alpha % -0.09% -0.26% -0.30% -0.18% -0.90%
Median alpha -0.09% -0.37% -1.03% -2.18% -9.75%
Hit rate (α>0) 48.1% 46.6% 45.2% 44.4% 38.6%
p (naive) <0.001 <0.001 <0.001 0.0005 <0.001
p (HAC) <0.001 <0.001 <0.001 0.0048 0.0002
N 184,985 178,639 176,896 173,819 165,354
Observed 20-day lift (vertical line) against the null distribution of random-date firing. If the line is deep inside the null cloud, the signal adds no information. If it sits in the left tail, the signal is doing real work in that direction; in the right tail it ran inverted — random dates served the bearish case better than its own triggers did.
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — bearish 20-day observed lift versus random-date permutation null (200 iterations)
Permutation null detail — all horizons × each benchmark
200-iteration null: for each ticker, sample N random dates from its history (matching observed trigger count) and compute the same alpha. Both observed and null are baseline-centered per ticker (each ticker's own baseline alpha is subtracted), which removes the universe-selection lift that all surviving names share, so the comparison is about the trigger's timing. It does not put the null at zero: that baseline is a median, while a random date's expectation is the ticker's mean, so the null settles at the gap between the two — the right-skew of the ticker's own alpha distribution, positive for equities. Read observed minus null, not the absolute position of either column — which is also why these figures do not match the α columns in the tables above (those are raw, uncentered means). pperm = one-sided fraction of null iters with mean in the "signal was right" tail (right for bullish, left for bearish), so it runs from a floor of 0.005 (trigger dates beat every random draw in the claimed direction) to a 1.000 ceiling (every random draw served the claimed direction better — a reliably inverted signal, not an absent one). The floor is 1/(iterations + 1) and moves with the iteration count; the ceiling does not. Either end says the result was reliable, not that it was large: the gap between the line and the cloud can be a fraction of a percent and still reach an endpoint, and the transaction-cost floor in the caveats below would swallow a gap that small. Read the size off the α and hit-rate columns, the reliability off pperm.
Horizon Bench Observed lift Null mean Null 95% CI pperm
1d spxew +0.06% +0.08% [+0.07%, +0.10%] 0.005
1d spx +0.05% +0.09% [+0.08%, +0.10%] 0.005
1d msci +0.07% +0.09% [+0.08%, +0.11%] 0.005
5d spxew +0.31% +0.37% [+0.34%, +0.41%] 0.005
5d spx +0.23% +0.38% [+0.35%, +0.42%] 0.005
5d msci +0.23% +0.39% [+0.36%, +0.43%] 0.005
20d spxew +1.28% +1.20% [+1.14%, +1.27%] 0.995
20d spx +1.22% +1.23% [+1.17%, +1.30%] 0.358
20d msci +1.20% +1.24% [+1.19%, +1.30%] 0.085
60d spxew +3.04% +2.61% [+2.52%, +2.74%] 1.000
60d spx +3.29% +2.68% [+2.59%, +2.80%] 1.000
60d msci +3.28% +2.69% [+2.61%, +2.82%] 1.000
252d spxew +8.13% +5.60% [+5.41%, +5.78%] 1.000
252d spx +8.24% +5.93% [+5.75%, +6.11%] 1.000
252d msci +7.78% +5.85% [+5.68%, +6.03%] 1.000

Example triggers on US large-caps (2023+, mcap ≥ $30B)

Six recent bearish FRESH_52W_HIGH_LOW triggers on US mega-caps, ranked within this sample of six: the top three and the bottom three, with extreme outliers excluded. Ranking is relative, not absolute — where the signal did well across the sampled names, even the bottom three can have beaten the benchmark, so the alpha printed on each panel is what settles it. Both groups are tail outcomes by construction; read them as the range, not the typical result.

Best three of the six sampled
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — strongest bearish trigger #1 on a US mega-cap, showing the stock's OHLC candles, moving averages, signal-specific overlays, and the 20-day forward window Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — strongest bearish trigger #2 on a US mega-cap, showing the stock's OHLC candles, moving averages, signal-specific overlays, and the 20-day forward window Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — strongest bearish trigger #3 on a US mega-cap, showing the stock's OHLC candles, moving averages, signal-specific overlays, and the 20-day forward window
Weakest three of the six sampled — not necessarily losses
Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — weakest bearish trigger #1 on a US mega-cap, showing the 20-day forward window where the signal failed Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — weakest bearish trigger #2 on a US mega-cap, showing the 20-day forward window where the signal failed Fresh 52-Week High / Low (with cooldown) (fresh_52w_high_low) — weakest bearish trigger #3 on a US mega-cap, showing the 20-day forward window where the signal failed
Stock-regime quadrants (2×2 per-stock, 20d alpha detail table)
Each quadrant groups triggers by the stock's own ADX(14) and RV(20) at the trigger date — the textbook conditioning variable (not market-level). Stock %, bench %, alpha %, and HAC p-value shown for each benchmark.
Quadrant N Stock % (spxew) Bench % (spxew) Alpha % (spxew) p (HAC) Stock % (spx) Bench % (spx) Alpha % (spx) p (HAC) Stock % (msci) Bench % (msci) Alpha % (msci) p (HAC)
Trending + Low vol Clean directional grind, low whipsaw 16,814 -0.71% +0.77% -1.48% <0.001 -0.71% +1.08% -1.77% <0.001 -0.71% +0.93% -1.63% <0.001
Trending + High vol Crisis selloff or parabolic rally 76,873 +1.75% +1.04% +0.65% <0.001 +1.75% +1.45% +0.34% <0.001 +1.75% +1.29% +0.45% <0.001
Non-trending + Low vol Quiet chop, summer doldrums 16,392 -0.96% +0.71% -1.67% <0.001 -0.96% +1.03% -1.99% <0.001 -0.96% +0.89% -1.86% <0.001
Non-trending + High vol Classical "whipsaw zone" for momentum 79,293 +0.77% +0.97% -0.25% <0.001 +0.77% +1.29% -0.51% <0.001 +0.77% +1.17% -0.42% <0.001
Sub-period breakdown table (20d alpha)
Historical clustering check. If alpha concentrates in one era, the signal's robustness is questionable.
Period N Alpha % (spxew) p (HAC) Alpha % (spx) p (HAC) Alpha % (msci) p (HAC)
2015-2019 2015-01-01 → 2020-01-01 59,166 -0.59% <0.001 -0.65% <0.001 -0.42% <0.001
2020-2022 2020-01-01 → 2023-01-01 62,936 +0.27% <0.001 +0.06% 0.2814 +0.25% <0.001
2023-2026 2023-01-01 → 2099-01-01 68,557 -0.08% 0.1271 -0.62% <0.001 -0.70% <0.001

Methodology and caveats

How to read. Entry at open of T+1 (one trading day after the signal fires on close of T). 20d = open T+1 to close T+20. Alpha = stock return − benchmark return over the same window (Convention A, single-sided, textbook). For bullish triggers, POSITIVE alpha = signal was right. For bearish triggers, NEGATIVE alpha = signal was right (stock underperformed market). No sign-flipping; the direction of the bet determines what "good" looks like. Per-stock regime is each stock's own ADX(14) and RV(20) at the trigger date — not market-wide state.

Three p-values, three robustness tests. (a) p_naive: scipy one-sample t-test on winsorized alphas. Optimistic because overlapping 20d windows on the same ticker inflate effective N. (b) p_hac: Newey-West HAC with lag = horizon — corrects for the overlap and is the academic-finance standard. (c) p_perm: one-sided fraction of 200 random-date null iterations falling in the “signal was right” tail (mean ≥ observed for bullish; mean ≤ observed for bearish). Tests whether the signal beats random date selection at all. A signal that clears all three (pnaive, phac, pperm all < 0.05) has real information; a signal that fails pperm has not beaten random timing whatever the t-test says — and because the test is one-sided, a pperm up at its 1.000 ceiling is not "no edge" but inverted edge: every random draw served the claimed direction better than the trigger dates did.

Caveats. (i) Universe reflects today's active tickers; delisted losers pruned → survivorship bias. (ii) Mcap ≥ $100M filter uses today's snapshot, not point-in-time — mild lookahead on which stocks enter the sample, not on returns. (iii) Means and p-values use winsorized alphas (1/99 percentile) to prevent data errors from dominating. Medians and hit rates use raw data. (iv) Zero transaction costs assumed. Realistic bid-ask + commissions remove 20–40bps from 20d alpha on US large-caps, more on small-cap. Sub-20bps alpha is noise in practice. (v) Past performance does not predict future results.

How to use this

1 · When to reach for this signal

Use Fresh 52-Week High / Low (with cooldown) bullish as a long-side screening tile. Bullish 20d alpha is +0.56% and beats random (permutation test, 200 iterations). Bearish 20d alpha is -0.12% — worse than random : firing on random dates would have done better.

These verdicts are 20-day holds vs S&P 500 Equal Weight. Longer horizons can differ in either direction — check the permutation detail tables below before extrapolating.

2 · When it works — the setups that drive it

  • Best bullish setup: Trending + High vol — alpha +0.66% / 20d on 118,686 historical triggers.
  • Best bearish setup: Non-trending + Low vol — alpha -1.67% / 20d on 16,392 historical triggers.
  • Best era for bullish: 2023-2026 — alpha +0.88% / 20d on 115,094 triggers.
  • Best era for bearish: 2015-2019 — alpha -0.59% / 20d on 59,166 triggers.

3 · When it fails — common false positives

  • Weakest bullish cell: Non-trending + Low vol — alpha +0.38% / 20d on 24,471 triggers.
  • Weakest bearish cell: Trending + High vol — alpha +0.65% / 20d on 76,873 triggers.
  • Worst era for bullish: 2015-2019 — alpha +0.06% / 20d on 60,537 triggers.
  • Worst era for bearish: 2020-2022 — alpha +0.27% / 20d on 62,936 triggers.

Signal-specific failure patterns

It works, but as a momentum-continuation tile, not a discovery tile
The 20-day cooldown reduces trigger volume by ~5x vs new_52w_high. The remaining alpha against equal-weight is positive but modest at short horizons and compounds at longer ones — see the at-a-glance table for current values. Mechanism: stocks making fresh 52-week highs after a quiet period have institutional accumulation behind them. Treat it as a quality-confirmation signal, not a discovery edge.
Selection bias: by the time it fires, the move is mature
A stock making its first 52-week high in 20+ sessions has already rallied significantly from its 52-week low. The forward edge here comes from continued accumulation in genuine winners, not from a low-priced bounce. Position sizing should reflect this: small per-name, longer holding period, expect the alpha at horizon scale rather than days.
Edge is small and not significant on equal-weight
Fresh 52w low (52w new low with 20-day cooldown) shows a small bearish point estimate against equal-weight, but the random-date null check does not separate it from noise. See the at-a-glance table for current numbers. Treat it as a watchlist signal rather than a directional short trigger on its own.
Bounces and short squeezes contaminate longer holds
Even when the 20-day window shows weakness, holding past 30 trading days exposes the trade to recovery dynamics: capitulation lows often precede sharp short-covering bounces. Keep horizons short if used at all.

4 · Pairing inside a screen

The statements below describe how this signal relates to others by construction — which indicator family it belongs to, and where same-family redundancy might reduce the independence of evidence inside a Daily Report. These are taxonomic classifications drawn from standard technical-analysis texts; they are not pairing backtests. Measured pair results — same-day co-fires put through the pair backtest — follow under “Measured pairings” below.

Breakout-family redundancy

Fresh 52-week high, new 52-week high, and new 20-day high are breakout signals at different lookbacks — all fire when price exceeds the maximum of the prior N bars (Edwards & Magee, Technical Analysis of Stock Trends, 11th ed. 2018; Kirkpatrick & Dahlquist, Technical Analysis, 3rd ed. 2015; Bulkowski, Encyclopedia of Chart Patterns, 3rd ed. 2021). Stacking two or more in the same direction within a single Daily Report produces correlated rather than independent evidence.

Breakdown-family redundancy

Fresh 52-week low, new 52-week low, and new 20-day low are breakdown signals at different lookbacks — all fire when price falls below the minimum of the prior N bars (Edwards & Magee, Technical Analysis of Stock Trends, 11th ed. 2018; Kirkpatrick & Dahlquist, Technical Analysis, 3rd ed. 2015; Bulkowski, Encyclopedia of Chart Patterns, 3rd ed. 2021). Stacking two or more in the same direction within a single Daily Report produces correlated rather than independent evidence.

Measured pairings — Bonferroni survivors

Beyond the literature pairings above, these are the same-day co-fire combinations involving Fresh 52-Week High / Low (with cooldown) that cleared the pair backtest's Bonferroni cut on the full 2016–2026 sample (549 pairs × 5 horizons = 2,745 hypotheses), on universes filtered to ADV ≥ $5M, price ≥ $5 and market cap ≥ $100M. That cut is two-sided: it asks only whether the co-fire's α is reliably different from zero, in either direction, so a pair can survive by reliably underperforming — 3 of the 6 rows below do exactly that (negative full-sample α). The same run holds out 2023+: the Test columns are that held-out window, printed for every row with enough held-out co-fires to measure, so a survivor that did not repeat out of sample is visible rather than hidden. All α figures here are for holding the stock long after the co-fire — no shorting assumed, and no sign flip for bearish legs. So positive α means the co-fire was followed by outperformance and negative α by underperformance, whichever way either leg points — a bearish leg does not flip the reading. Survivors are rare by design — absence of a pair here means it did not clear the cut, not that it was untested. Ranked by held-out (2023+) α. Historical tendencies, not recommendations.

Pairs carry the underlying split names: fresh_52w_high is this signal's bullish side, fresh_52w_low its bearish side.

US (NYSE / NASDAQ / AMEX)

Pair (same-day co-fire, long) Full α Test α (2023+) Test N p_perm test
fresh_52w_low bearish + stochastics bullish -1.31% -1.85% 619 0.002
fresh_52w_high bullish + new_20d_low bearish -3.37% — — —

2 of this universe's 18 surviving pairs involve this signal · α vs ^SPXEW.

China A-shares — 4 surviving pairs
Pair (same-day co-fire, long) Full α Test α (2023+) Test N p_perm test
bollinger bullish + fresh_52w_low bearish +1.51% +2.23% 681 0.002
fresh_52w_low bearish + weekly_change bearish +2.48% +0.05% 2,838 0.906
double_bottom_breakdown bearish + fresh_52w_low bearish +0.87% -0.74% 1,186 0.058
bollinger bearish + fresh_52w_low bearish -7.10% — — —

4 of this universe's 138 surviving pairs involve this signal · α vs 83188.HK.

China A-share survivor α runs large but skews toward small-caps, where trading costs and thin liquidity claim a large share of any measured edge — screening context, not a capturable spread.

“—” in the test columns means the held-out 2023+ sample fell below the 20-observation minimum this run requires before it computes any statistic, so no out-of-sample figure exists for that pair — not that it never co-fired again. Those pairs rank last.

What would likely rescue this signal

This block calls out the data or conditions that could turn a technically weak signal into a usable one in a composite screen. Based on signal mechanics and the observed failure patterns above; individual combinations are not yet backtested.

  • Pair with positive market breadth — Fresh highs in narrow-breadth markets are low-quality leadership. Gate on advance-decline ratio above 1.5 over trailing 10 sessions to avoid concentration risk.
  • Consolidation-base filter — Fresh high from a tight-range base (last 20d range below 5% of average price) is structurally different from fresh high after a vertical rally. Range-filter testable from OHLC.
  • Fundamental gate — A 52-week high with positive earnings revision in the last 30 days is a different bet from one without.
  • Volume-confirm the capitulation — Fresh 52w low on 2x average volume vs thin volume is different in nature. Volume filter may concentrate alpha. Testable.
  • Time-stop strictly at 20 trading days — Signal dies beyond 20-30 days due to recovery dynamics. Enforce time stop.

See also Why technical-only signals don't survive on their own for the broader argument.

5 · Before acting — a 5-point checklist

  1. Normal trading day? Rule out earnings (within ±3 days), ex-dividend, or known corporate-action dates — the signal is almost certainly reading noise, not momentum, in those windows.
  2. Where is price vs its own 50 / 200 DMA? A trend signal is only as credible as the underlying trend it claims to confirm. Check the 200DMA orientation before acting.
  3. What's the sector breadth doing? An isolated signal in a broadly down-trending sector is a lower-confidence setup than one firing with the rest of its peer group.
  4. Is ADV20 enough for the intended size? A $1M notional order in a $500M name moves the tape by itself. A useful floor is adv20d ≥ 5% of the intended position.
  5. What invalidates the trade? Define a price level in advance (for longs: a close below the trigger-day low; for shorts: a close above the trigger-day high) and honour it. The backtest alpha is an average; any single trade can land at either tail.

Execution notes

Use as a long-side qualifier with momentum continuation as the underlying mechanism. Entry open T+1. Longer horizons can look stronger in raw alpha, but check the same horizon's permutation row before treating the 1-year column as the headline — a raw number that fails the random-date test is not edge. The test is one-sided, so read which end of the p range it failed at: near the ceiling means the trigger dates did worse than random dates in the claimed direction, which is inverted rather than merely absent. Pair with breadth or quality filters to reduce concentration risk. New lows side: Marginal short-side tile. Entry open T+1, hold no more than 20 trading days. Volume confirmation (capitulation on above 2x average) is structurally different from a thin-volume drift to lows; the volume version may concentrate the edge.