Trend weekly_change

Weekly Price Change

Triggers when the absolute price change over the last 5 trading days exceeds the threshold. Bullish if up, bearish if down.

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
threshold_pct Minimum absolute change (%) 10 1–50

Historical context

3,664,133 triggers on 23,631 tickers, 1988-03-31 → 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 -0.16% +0.84%
20-day +0.56% +1.59%
60-day +1.56% +2.49%
1-year +9.80% +9.85%
Random-date null check (20-day): Bullish: inside null (p=0.831).
Bearish: worse than random (p=1.000).

Where does WEEKLY_CHANGE 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.

Weekly Price Change (weekly_change) — trigger count distribution by per-stock regime quadrant (trending/non-trending × high/low realized volatility) for bullish and bearish triggers, global universe

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.

Weekly Price Change (weekly_change) — mean 20-day alpha versus S&P 500 Equal Weight by per-stock regime quadrant, bullish and bearish triggers side by side
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.

Weekly Price Change (weekly_change) — 20-day alpha split by historical sub-period (2015-2019, 2020-2022, 2023+) to check consistency across market regimes

↑ Bullish triggers

Bench Metric 1d 5d 20d 60d 252d
spxew Stock % -0.09% +0.16% +1.65% +4.59% +22.67%
Bench % +0.06% +0.29% +1.17% +3.07% +12.89%
Alpha % -0.15% -0.16% +0.56% +1.56% +9.80%
Median alpha -0.30% -0.96% -1.93% -4.07% -8.61%
Hit rate (α>0) 45.5% 44.4% 44.3% 42.9% 42.7%
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 2,067,047 1,987,482 1,970,553 1,918,053 1,688,840
spx Stock % -0.09% +0.16% +1.65% +4.59% +22.67%
Bench % +0.03% +0.32% +1.32% +3.77% +15.72%
Alpha % -0.13% -0.17% +0.39% +0.85% +7.07%
Median alpha -0.29% -1.00% -2.11% -4.83% -11.73%
Hit rate (α>0) 45.6% 44.1% 43.8% 41.6% 40.3%
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 2,084,305 2,019,378 1,993,058 1,941,731 1,719,649
msci Stock % -0.09% +0.16% +1.65% +4.59% +22.67%
Bench % +0.06% +0.30% +1.16% +3.34% +13.38%
Alpha % -0.15% -0.17% +0.54% +1.28% +9.05%
Median alpha -0.32% -1.00% -1.97% -4.41% -9.67%
Hit rate (α>0) 45.2% 44.1% 44.2% 42.3% 41.8%
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 2,066,998 1,996,522 1,982,863 1,926,962 1,694,529
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.
Weekly Price Change (weekly_change) — 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 +0.05% +0.12% [+0.12%, +0.13%] 1.000
1d spx +0.06% +0.13% [+0.13%, +0.14%] 1.000
1d msci +0.06% +0.14% [+0.13%, +0.14%] 1.000
5d spxew +0.38% +0.57% [+0.56%, +0.58%] 1.000
5d spx +0.41% +0.59% [+0.58%, +0.60%] 1.000
5d msci +0.41% +0.59% [+0.58%, +0.60%] 1.000
20d spxew +1.83% +1.84% [+1.82%, +1.86%] 0.831
20d spx +1.88% +1.86% [+1.84%, +1.88%] 0.035
20d msci +1.93% +1.87% [+1.85%, +1.90%] 0.005
60d spxew +3.24% +3.87% [+3.84%, +3.91%] 1.000
60d spx +3.30% +3.93% [+3.89%, +3.97%] 1.000
60d msci +3.33% +3.96% [+3.92%, +4.00%] 1.000
252d spxew +4.86% +5.73% [+5.65%, +5.81%] 1.000
252d spx +6.23% +6.11% [+6.03%, +6.20%] 0.010
252d msci +6.00% +6.00% [+5.92%, +6.09%] 0.517

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

Six recent bullish WEEKLY_CHANGE 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
Weekly Price Change (weekly_change) — 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 Weekly Price Change (weekly_change) — 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 Weekly Price Change (weekly_change) — 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
Weekly Price Change (weekly_change) — weakest bullish trigger #1 on a US mega-cap, showing the 20-day forward window where the signal failed Weekly Price Change (weekly_change) — weakest bullish trigger #2 on a US mega-cap, showing the 20-day forward window where the signal failed Weekly Price Change (weekly_change) — 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 3,373 +27.35% +1.21% +26.08% <0.001 +27.35% +1.49% +25.70% <0.001 +27.35% +1.46% +25.77% <0.001
Trending + High vol Crisis selloff or parabolic rally 1,310,815 +1.61% +1.17% +0.54% <0.001 +1.61% +1.33% +0.34% <0.001 +1.61% +1.15% +0.53% <0.001
Non-trending + Low vol Quiet chop, summer doldrums 210 +3.79% +0.73% +2.88% 0.0140 +3.79% +0.96% +2.67% 0.0234 +3.79% +0.79% +2.83% 0.0157
Non-trending + High vol Classical "whipsaw zone" for momentum 798,675 +1.45% +1.14% +0.36% <0.001 +1.45% +1.27% +0.22% <0.001 +1.45% +1.16% +0.33% <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 → 2020-01-01 476,630 -0.41% <0.001 -0.63% <0.001 -0.45% <0.001
2020-2022 2020-01-01 → 2023-01-01 770,183 +0.39% <0.001 +0.61% <0.001 +0.80% <0.001
2023-2026 2023-01-01 → 2099-01-01 895,973 +1.25% <0.001 +0.76% <0.001 +0.86% <0.001

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

Bench Metric 1d 5d 20d 60d 252d
spxew Stock % +0.16% +1.03% +3.33% +6.88% +24.82%
Bench % +0.05% +0.16% +1.65% +4.42% +14.64%
Alpha % +0.11% +0.84% +1.59% +2.49% +9.85%
Median alpha +0.03% +0.34% -0.11% -1.77% -7.18%
Hit rate (α>0) 50.4% 52.1% 49.6% 46.7% 43.8%
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 1,476,636 1,433,028 1,420,026 1,376,329 1,271,926
spx Stock % +0.16% +1.03% +3.33% +6.88% +24.82%
Bench % +0.03% +0.27% +1.93% +4.80% +17.25%
Alpha % +0.12% +0.75% +1.38% +2.09% +7.79%
Median alpha +0.04% +0.27% -0.34% -2.26% -9.79%
Hit rate (α>0) 50.6% 51.6% 48.9% 45.9% 41.8%
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 1,487,885 1,444,260 1,439,886 1,391,775 1,296,666
msci Stock % +0.16% +1.03% +3.33% +6.88% +24.82%
Bench % +0.02% +0.27% +1.78% +4.53% +15.11%
Alpha % +0.13% +0.74% +1.50% +2.52% +8.94%
Median alpha +0.04% +0.25% -0.23% -1.82% -8.15%
Hit rate (α>0) 50.5% 51.5% 49.3% 46.6% 42.9%
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 1,479,449 1,433,593 1,422,315 1,384,853 1,268,845
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.
Weekly Price Change (weekly_change) — 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 +0.30% +0.12% [+0.12%, +0.13%] 1.000
1d spx +0.29% +0.13% [+0.12%, +0.13%] 1.000
1d msci +0.34% +0.13% [+0.13%, +0.14%] 1.000
5d spxew +1.42% +0.56% [+0.55%, +0.57%] 1.000
5d spx +1.36% +0.58% [+0.56%, +0.59%] 1.000
5d msci +1.36% +0.58% [+0.57%, +0.59%] 1.000
20d spxew +3.15% +1.81% [+1.78%, +1.83%] 1.000
20d spx +3.16% +1.82% [+1.80%, +1.85%] 1.000
20d msci +3.17% +1.84% [+1.81%, +1.87%] 1.000
60d spxew +5.25% +3.80% [+3.75%, +3.84%] 1.000
60d spx +5.61% +3.86% [+3.81%, +3.90%] 1.000
60d msci +5.63% +3.88% [+3.84%, +3.93%] 1.000
252d spxew +9.21% +6.47% [+6.38%, +6.55%] 1.000
252d spx +11.04% +6.84% [+6.75%, +6.92%] 1.000
252d msci +10.30% +6.74% [+6.65%, +6.82%] 1.000

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

Six recent bearish WEEKLY_CHANGE 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
Weekly Price Change (weekly_change) — 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 Weekly Price Change (weekly_change) — 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 Weekly Price Change (weekly_change) — 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
Weekly Price Change (weekly_change) — weakest bearish trigger #1 on a US mega-cap, showing the 20-day forward window where the signal failed Weekly Price Change (weekly_change) — weakest bearish trigger #2 on a US mega-cap, showing the 20-day forward window where the signal failed Weekly Price Change (weekly_change) — 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 414 +0.70% +1.60% -0.69% 0.8045 +0.70% +2.36% -1.46% 0.6050 +0.70% +1.79% -1.11% 0.6994
Trending + High vol Crisis selloff or parabolic rally 880,166 +4.08% +1.89% +2.12% <0.001 +4.08% +2.20% +1.85% <0.001 +4.08% +2.01% +2.02% <0.001
Non-trending + Low vol Quiet chop, summer doldrums 38 +3.98% +1.92% +2.35% <0.001 +3.98% +2.14% +1.89% 0.0005 +3.98% +2.04% +1.98% <0.001
Non-trending + High vol Classical "whipsaw zone" for momentum 623,711 +2.31% +1.35% +0.89% <0.001 +2.31% +1.56% +0.76% <0.001 +2.31% +1.44% +0.80% <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 → 2020-01-01 359,485 +1.21% <0.001 +1.24% <0.001 +1.48% <0.001
2020-2022 2020-01-01 → 2023-01-01 583,619 +1.17% <0.001 +1.11% <0.001 +1.41% <0.001
2023-2026 2023-01-01 → 2099-01-01 576,368 +2.30% <0.001 +1.76% <0.001 +1.62% <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

Not a standalone entry trigger at 20 days. Bullish 20d alpha is +0.56% — inside the null : indistinguishable from random timing. Bearish 20d alpha is +1.59% — worse than random : firing on random dates would have done better. Fires are screening context inside a composite (section 4), not entries.

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 +0.54% / 20d on 1,310,815 historical triggers.
  • Least-bad bearish cell: Non-trending + High vol — alpha +0.89% / 20d on 623,711 triggers — still wrong-signed; no bearish cell produced negative alpha.
  • Best era for bullish: 2023-2026 — alpha +1.25% / 20d on 895,973 triggers.
  • Least-bad era for bearish: 2020-2022 — alpha +1.17% / 20d on 583,619 triggers — still wrong-signed; no era produced negative alpha.

3 · When it fails — common false positives

  • Weakest bullish cell: Non-trending + High vol — alpha +0.36% / 20d on 798,675 triggers.
  • Weakest bearish cell: Trending + High vol — alpha +2.12% / 20d on 880,166 triggers.
  • Worst era for bullish: 2015-2019 — alpha -0.41% / 20d on 476,630 triggers.
  • Worst era for bearish: 2023-2026 — alpha +2.30% / 20d on 576,368 triggers.

Signal-specific failure patterns

By construction it describes the past week — it does not forecast
The trigger fires when the absolute close-to-close change over the trailing 5 trading days meets or exceeds the threshold — default 10%, user-adjustable from 1% to 50% in the report builder — with direction set by the sign of the move. It is a fixed-threshold rate-of-change trigger, not a percentile rank of the universe. A fire records that a large move already happened; any forward edge must come from continuation or reversal tendencies, which are horizon- and regime-dependent. See the at-a-glance table and the permutation-null line above for whether either direction currently carries timing content.
Big movers are a biased subset — raw alpha mixes stock selection with timing
Names that move 10% in a week are disproportionately high-beta, news-driven, and smaller-cap. Alpha versus an index therefore mixes what kind of stock triggers with when it triggers. The random-date permutation null — re-firing the same number of triggers per ticker at random dates — is the honest test of timing content here; read that line rather than the raw alpha before treating either direction as evidence.
Bearish fires often mark completed repricings, and bounce mechanics can dominate
A stock down 10%+ in a week has usually just repriced on a catalyst — earnings, guidance, litigation, financing. From there, panic overshoot mean-reverts while genuine deterioration continues, and which effect dominates changes with horizon and regime. If the longer-horizon bearish columns in the current tables show positive alpha, the bounce is dominating — in that state, treat a bearish fire as volatility and catalyst context, not a short entry.

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.

Rate-of-change family

Weekly percent change is a rate-of-change (ROC) measure of price momentum. It is related to but distinct from the normalised oscillator family (RSI, Stochastics, Williams %R, CCI) — ROC measures raw percent change and is unbounded, while the oscillators scale price against a recent range or average deviation (Kirkpatrick & Dahlquist, Technical Analysis, 3rd ed. 2015). Pairing weekly_change with an oscillator in the same direction produces partially overlapping evidence rather than fully independent confirmation.

Measured pairings — Bonferroni survivors

Beyond the literature pairings above, these are the same-day co-fire combinations involving Weekly Price Change 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 — 7 of the 44 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.

US (NYSE / NASDAQ / AMEX)

Pair (same-day co-fire, long) Full α Test α (2023+) Test N p_perm test
new_20d_low bearish + weekly_change bearish +0.61% +1.06% 25,567 0.002
stochastics bearish + weekly_change bullish +0.52% +1.06% 9,020 0.002
rsi bullish + weekly_change bearish +1.10% +0.97% 1,931 0.004
bollinger bullish + weekly_change bearish +0.97% +0.45% 6,480 0.010
hh_hl_structure bullish + weekly_change bullish -2.78% -1.15% 192 0.437

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

Europe — 1 surviving pair
Pair (same-day co-fire, long) Full α Test α (2023+) Test N p_perm test
bullish_trend_breakdown bearish + weekly_change bearish +1.75% +3.21% 359 0.002

1 of this universe's 20 surviving pairs involves this signal · α vs ^STOXX.

Hong Kong — 8 surviving pairs
Pair (same-day co-fire, long) Full α Test α (2023+) Test N p_perm test
rsi bearish + weekly_change bullish +2.14% +1.63% 498 0.024
bollinger bearish + weekly_change bullish +1.23% +1.32% 1,479 0.002
hh_hl_streak bullish + weekly_change bullish +1.47% +1.18% 1,411 0.004
stochastics bearish + weekly_change bullish +1.29% +1.18% 1,528 0.004
new_20d_high bullish + weekly_change bullish +0.89% +1.05% 5,551 0.002
volume_breakout bullish + weekly_change bullish +1.10% +0.93% 2,818 0.006
weekly_change bullish + williams_r bearish +1.49% +0.77% 1,235 0.106
new_20d_low bearish + weekly_change bearish +1.09% +0.33% 2,979 0.200

8 of this universe's 23 surviving pairs involve this signal · α vs ^HSI.

China A-shares — 30 surviving pairs
Pair (same-day co-fire, long) Full α Test α (2023+) Test N p_perm test
volume_breakout bullish + weekly_change bearish +7.63% +15.53% 1,349 0.002
rsi bullish + weekly_change bullish +4.70% +11.50% 207 0.002
failed_double_bottom bullish + weekly_change bearish +9.65% +10.09% 73 0.002
volume_breakout bearish + weekly_change bearish +3.53% +9.30% 5,524 0.002
ma_crossover bearish + weekly_change bullish +3.90% +7.89% 249 0.002
weekly_change bearish + williams_r bullish +5.32% +7.51% 7,294 0.002
rsi bullish + weekly_change bearish +6.13% +6.96% 3,592 0.002
ma_crossover bearish + weekly_change bearish +4.75% +6.71% 584 0.002
bollinger bullish + weekly_change bearish +4.57% +6.33% 12,186 0.002
stochastics bullish + weekly_change bearish +4.27% +5.57% 14,105 0.002
hh_hl_structure bearish + weekly_change bearish +3.55% +4.88% 130 0.002
failed_double_top bearish + weekly_change bearish +3.04% +4.34% 1,298 0.002
hh_hl_structure bullish + weekly_change bearish +1.97% +4.24% 2,410 0.002
new_20d_low bearish + weekly_change bearish +3.22% +3.68% 50,447 0.002
cci bullish + weekly_change bearish +2.67% +3.62% 1,244 0.002
hh_hl_streak bearish + weekly_change bearish +2.33% +2.87% 14,066 0.002
hh_hl_structure bearish + weekly_change bullish +1.95% +2.68% 1,683 0.002
vwap_cross bearish + weekly_change bearish +1.13% +2.59% 7,352 0.002
hh_hl_streak bullish + weekly_change bullish +0.92% +2.06% 22,970 0.002
vwap_cross bullish + weekly_change bullish +0.64% +1.42% 12,597 0.002
double_bottom_breakdown bearish + weekly_change bearish +2.40% +1.39% 2,563 0.002
macd bullish + weekly_change bullish +0.51% +1.25% 15,314 0.002
macd bearish + weekly_change bearish +0.76% +0.72% 9,155 0.002
volume_breakout bullish + weekly_change bullish -0.45% +0.52% 61,873 0.002
weekly_change bullish + williams_r bearish -0.37% +0.43% 28,381 0.002
new_20d_high bullish + weekly_change bullish -0.56% +0.15% 83,483 0.010
fresh_52w_low bearish + weekly_change bearish +2.48% +0.05% 2,838 0.906
volume_breakout bearish + weekly_change bullish -1.12% -0.13% 15,550 0.331
double_top_breakout bullish + weekly_change bullish -1.05% -0.28% 5,955 0.228
hh_hl_structure bullish + weekly_change bullish -4.80% -4.40% 305 0.002

30 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.

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.

  • Read a persistently inverted bearish side as a bounce indicator — If the bearish side shows positive alpha at longer horizons in the current tables — and keeps doing so across backtest re-runs — the signal is functionally a drawdown-bounce indicator rather than a short trigger, and the honest usage is to flip its interpretation: bearish fires become candidates for mean-reversion review, not short entries. Whether that state holds is visible in the tables above.
  • Raise the threshold to concentrate on catalysts — The default 10% threshold casts a wide net. Raising it in the report builder (e.g. to 15-20%) concentrates triggers in catalyst-driven events — earnings surprises, M&A, clinical readouts — where post-event behavior is a distinct, better-studied phenomenon, at the cost of far fewer fires.
  • Condition on the volatility regime — A 10% weekly move in a compressed-volatility market is usually a single-stock event; in a crisis it is market-wide, and the forward behavior differs. The tables above already split results by trend state (ADX at the 25 threshold) and realized-volatility regime — use those rows to judge whether the current regime supports acting on fires at all.

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

The most defensible use is as a SCREENING LENS — a fast way to surface the stocks that moved most this week — rather than as a predictive trigger. A double-digit weekly move is a descriptive fact about price action, which is why the signal appears on so many charts. Treat a side as a trade screen only if it beats the random-date permutation null in the current tables; otherwise use fires to prioritise what to investigate. Note that a fixed threshold means different things across sectors and volatility regimes — a 10% week is routine for a small biotech and extraordinary for a mega-cap utility. Historical tendency, not a recommendation.

See a live screen of this signal

Curated Daily Reports that screen for this signal, refreshed at the open, midday and close — free to view, no account needed: