Trend hh_hl_streak

Highs/Lows streak

Detects sustained trend structure. Bullish: N consecutive days of higher highs AND higher lows. Bearish: N consecutive days of lower lows AND lower highs. Triggers on the day the streak is first confirmed.

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
streak Minimum consecutive days 3 2–10

Historical context

463,719 valid triggers on 3,464 distinct tickers between 2015-03-30 and 2026-04-22. Universe: us_only · mcap ≥ $100,000,000 · price ≥ $1 (3,497 tickers). Entry at open T+1. 1d = intraday T+1; 20d = open T+1 to close T+20.

Benchmarks: spxew (S&P 500 Equal Weight — the primary benchmark here; a median-stock view that avoids the 2020+ megacap-concentration distortion), spx (S&P 500, cap-weighted), and msci (MSCI World USD). Per-stock regime: trending = ADX(14) ≥ 25, high vol = 20d ann. vol ≥ 20%.

At a glance (20d alpha vs S&P 500 Equal Weight, US-only)

Bullish
-0.07%
vs random-date null: worse than random (pperm=1.000)
Bearish (negative alpha = signal right)
+0.10%
vs random-date null: beats random (pperm=0.005)

Reading this: the random-date null is: for each ticker, sample N random dates and compute the same alpha — what alpha does a signal with no information produce? If the signal's observed alpha beats the null (pperm≤0.05), it's adding real information. If it's inside or worse than the null, the signal doesn't add value over random firing — any observed alpha is either noise or a universe artifact.

How often does HH_HL_STREAK fire in each regime?

The signal's bucket distribution is itself informative. If 50%+ of all HH_HL_STREAK triggers fire in the "non-trending + high vol" quadrant, the signal is structurally a chop-market event — regardless of what its textbook definition claims. Bullish and bearish are shown separately; counts are across the full US-only sample after the mcap and price floor.

Highs/Lows streak (hh_hl_streak) — trigger count distribution by per-stock regime quadrant (trending/non-trending × high/low realized volatility) for , US-only universe

Per-stock regime quadrant — 20d alpha

Each trigger is tagged with the host stock's own technical regime on the trigger date: is the stock itself in a trend (ADX(14) ≥ 25) or ranging? And is its realized 20-day volatility high (≥ 20% annualized) or low? This is the textbook conditioning variable — "does this signal work better in trending stocks?" — answered at the level of the individual stock, not the market. Positive bars are good for the signal; negative bars mean alpha vanishes into the benchmark or worse.

Highs/Lows streak (hh_hl_streak) — mean 20-day alpha versus S&P 500 Equal Weight by per-stock regime quadrant,  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.

Sub-period check — does the signal work in every era?

A multi-year average can hide major instability. We split the sample into three non-overlapping windows: 2015–2019 (pre-COVID, normalized monetary policy), 2020–2022 (pandemic crash + recovery + rate-shock bear), and 2023+ (post-ZIRP, AI megacap rally). If a signal's alpha is positive overall but comes entirely from one era, that's a red flag — the conditions that produced it may not repeat. A robust signal shows a consistent sign across all non-empty buckets.

Highs/Lows streak (hh_hl_streak) — 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
spx Stock % -0.04% +0.07% +0.67% +2.09% +10.93%
Bench % +0.01% +0.23% +0.99% +2.81% +13.34%
Alpha % -0.05% -0.15% -0.28% -0.72% -2.41%
Median alpha -0.05% -0.22% -0.70% -1.97% -8.49%
Hit rate (α>0) 48.7% 47.5% 46.3% 44.5% 39.5%
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 244,927 243,861 241,448 237,745 214,646
msci Stock % -0.04% +0.07% +0.67% +2.09% +10.93%
Bench % +0.04% +0.22% +0.85% +2.37% +10.93%
Alpha % -0.08% -0.14% -0.14% -0.24% +0.05%
Median alpha -0.08% -0.20% -0.56% -1.46% -5.94%
Hit rate (α>0) 47.9% 47.7% 47.0% 45.8% 42.6%
p (naive) <0.001 <0.001 <0.001 <0.001 0.6189
p (HAC) <0.001 <0.001 <0.001 0.0013 0.8870
N 244,050 242,883 240,490 236,476 213,637
spxew Stock % -0.04% +0.07% +0.67% +2.09% +10.93%
Bench % +0.02% +0.16% +0.78% +2.02% +9.68%
Alpha % -0.06% -0.09% -0.07% +0.03% +1.36%
Median alpha -0.05% -0.14% -0.46% -1.19% -4.81%
Hit rate (α>0) 48.7% 48.4% 47.5% 46.6% 43.7%
p (naive) <0.001 <0.001 0.0026 0.5472 <0.001
p (HAC) <0.001 <0.001 0.0140 0.7355 <0.001
N 243,279 241,158 239,249 234,718 212,491
Distribution of all 20d alpha outcomes for this direction. Median and winsorized mean shown.
Highs/Lows streak (hh_hl_streak) — bullish 20-day alpha histogram showing distribution of per-trigger returns
Observed 20d alpha (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 a tail, the signal is doing real work in that direction.
Highs/Lows streak (hh_hl_streak) — bullish 20-day observed alpha versus random-date permutation null (200 iterations)
Permutation null detail — all horizons × both benchmarks
200-iteration null: for each ticker, sample N random dates from its history (matching observed trigger count) and compute the same alpha. The null distribution's 95% CI is where a signal with no information would land. pperm = one-sided fraction of null iters with mean ≥ observed.
Horizon Bench Observed α Null mean Null 95% CI pperm
1d spx -0.05% -0.02% [-0.03%, -0.00%] 1.000
1d msci -0.08% -0.04% [-0.05%, -0.03%] 1.000
1d spxew -0.06% -0.04% [-0.05%, -0.03%] 1.000
5d spx -0.15% +0.03% [-0.00%, +0.07%] 1.000
5d msci -0.14% +0.03% [-0.00%, +0.08%] 1.000
5d spxew -0.09% +0.05% [+0.02%, +0.10%] 1.000
20d spx -0.28% +0.14% [+0.09%, +0.22%] 1.000
20d msci -0.14% +0.27% [+0.21%, +0.34%] 1.000
20d spxew -0.07% +0.34% [+0.27%, +0.42%] 1.000
60d spx -0.72% +0.41% [+0.30%, +0.55%] 1.000
60d msci -0.24% +0.86% [+0.74%, +0.99%] 1.000
60d spxew +0.03% +1.08% [+0.98%, +1.22%] 1.000
252d spx -2.41% +1.59% [+1.25%, +1.87%] 1.000
252d msci +0.05% +3.92% [+3.61%, +4.21%] 1.000
252d spxew +1.36% +5.24% [+4.91%, +5.53%] 1.000

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

Six recent bullish HH_HL_STREAK triggers on US mega-caps, filtered to |alpha| ≤ 25% to exclude catalyst-driven outliers (earnings surprises, M&A, binary events). The first three are the strongest outcomes — what the signal looks like when it works. The last three are the weakest — what the signal looks like when it fails. Each chart shows the stock's price with signal-appropriate technical overlays (e.g. MACD subpanel on MACD pages, Bollinger Bands on Bollinger pages, the 52-week trailing max line on 52w-high pages), a dot marking the trigger date, and the forward window shaded (green when the signal was right, red when it wasn't). Click any chart to open full-size.

Strongest outcomes (what HH_HL_STREAK looks like when it works)
Weakest outcomes (what HH_HL_STREAK looks like when it fails)
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 % (spx) Bench % (spx) Alpha % (spx) p (HAC) Stock % (msci) Bench % (msci) Alpha % (msci) p (HAC) Stock % (spxew) Bench % (spxew) Alpha % (spxew) p (HAC)
Trending + Low vol Clean directional grind, low whipsaw 15,812 -0.02% +0.52% -0.49% <0.001 -0.02% +0.33% -0.29% <0.001 -0.02% +0.12% -0.09% 0.1162
Trending + High vol Crisis selloff or parabolic rally 78,384 +0.65% +1.16% -0.46% <0.001 +0.65% +0.98% -0.28% <0.001 +0.65% +0.90% -0.20% 0.0002
Non-trending + Low vol Quiet chop, summer doldrums 26,679 +0.22% +0.66% -0.43% <0.001 +0.22% +0.47% -0.23% <0.001 +0.22% +0.32% -0.07% 0.1155
Non-trending + High vol Classical "whipsaw zone" for momentum 124,133 +0.92% +1.02% -0.07% 0.0846 +0.92% +0.92% +0.03% 0.4682 +0.92% +0.89% +0.06% 0.1018
Sub-period breakdown table (20d alpha)
Historical clustering check. If alpha concentrates in one era, the signal's robustness is questionable.
Period N Alpha % (spx) p (HAC) Alpha % (msci) p (HAC) Alpha % (spxew) p (HAC)
2015-2019 2015-01-01 → 2020-01-01 71,102 -0.32% <0.001 -0.14% 0.0003 -0.08% 0.0347
2020-2022 2020-01-01 → 2023-01-01 79,675 +0.04% 0.4025 +0.20% <0.001 -0.12% 0.0280
2023-2026 2023-01-01 → 2099-01-01 94,231 -0.51% <0.001 -0.41% <0.001 +0.02% 0.7160

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

Bench Metric 1d 5d 20d 60d 252d
spx Stock % -0.02% +0.23% +0.99% +3.17% +13.16%
Bench % +0.02% +0.24% +1.11% +3.38% +14.22%
Alpha % -0.04% +0.01% -0.10% -0.22% -1.08%
Median alpha -0.04% -0.13% -0.57% -1.70% -8.72%
Hit rate (α>0) 49.0% 48.7% 47.2% 45.6% 40.0%
p (naive) <0.001 0.5593 0.0002 <0.001 <0.001
p (HAC) <0.001 0.5604 0.0018 0.0070 0.0048
N 218,651 218,448 217,255 211,683 192,182
msci Stock % -0.02% +0.23% +0.99% +3.17% +13.16%
Bench % +0.04% +0.23% +1.03% +3.03% +12.11%
Alpha % -0.05% +0.02% -0.01% +0.16% +1.02%
Median alpha -0.07% -0.14% -0.49% -1.31% -6.52%
Hit rate (α>0) 48.4% 48.6% 47.6% 46.6% 42.4%
p (naive) <0.001 0.1776 0.8435 0.0010 <0.001
p (HAC) <0.001 0.1786 0.8679 0.0511 0.0080
N 218,357 217,329 215,491 210,330 191,386
spxew Stock % -0.02% +0.23% +0.99% +3.17% +13.16%
Bench % +0.08% +0.23% +0.92% +2.80% +10.87%
Alpha % -0.09% +0.02% +0.10% +0.36% +2.39%
Median alpha -0.07% -0.11% -0.36% -1.07% -5.28%
Hit rate (α>0) 48.2% 48.8% 48.2% 47.1% 43.5%
p (naive) <0.001 0.2026 0.0002 <0.001 <0.001
p (HAC) <0.001 0.2037 0.0022 <0.001 <0.001
N 217,907 216,634 215,208 209,789 190,029
Distribution of all 20d alpha outcomes for this direction. Median and winsorized mean shown.
Highs/Lows streak (hh_hl_streak) — bearish 20-day alpha histogram showing distribution of per-trigger returns
Observed 20d alpha (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 a tail, the signal is doing real work in that direction.
Highs/Lows streak (hh_hl_streak) — bearish 20-day observed alpha versus random-date permutation null (200 iterations)
Permutation null detail — all horizons × both benchmarks
200-iteration null: for each ticker, sample N random dates from its history (matching observed trigger count) and compute the same alpha. The null distribution's 95% CI is where a signal with no information would land. pperm = one-sided fraction of null iters with mean ≥ observed.
Horizon Bench Observed α Null mean Null 95% CI pperm
1d spx -0.04% -0.02% [-0.04%, -0.01%] 0.015
1d msci -0.05% -0.04% [-0.06%, -0.03%] 0.154
1d spxew -0.09% -0.04% [-0.06%, -0.03%] 0.005
5d spx +0.01% +0.03% [-0.03%, +0.15%] 0.343
5d msci +0.02% +0.03% [-0.02%, +0.15%] 0.448
5d spxew +0.02% +0.05% [+0.00%, +0.17%] 0.080
20d spx -0.10% +0.12% [+0.03%, +0.23%] 0.005
20d msci -0.01% +0.24% [+0.15%, +0.35%] 0.005
20d spxew +0.10% +0.31% [+0.22%, +0.43%] 0.005
60d spx -0.22% +0.29% [+0.10%, +0.48%] 0.005
60d msci +0.16% +0.74% [+0.56%, +0.92%] 0.005
60d spxew +0.36% +0.97% [+0.78%, +1.15%] 0.005
252d spx -1.08% +0.97% [+0.59%, +1.42%] 0.005
252d msci +1.02% +3.30% [+2.92%, +3.75%] 0.005
252d spxew +2.39% +4.67% [+4.30%, +5.12%] 0.005

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

Six recent bearish HH_HL_STREAK triggers on US mega-caps, filtered to |alpha| ≤ 25% to exclude catalyst-driven outliers (earnings surprises, M&A, binary events). The first three are the strongest outcomes — what the signal looks like when it works. The last three are the weakest — what the signal looks like when it fails. Each chart shows the stock's price with signal-appropriate technical overlays (e.g. MACD subpanel on MACD pages, Bollinger Bands on Bollinger pages, the 52-week trailing max line on 52w-high pages), a dot marking the trigger date, and the forward window shaded (green when the signal was right, red when it wasn't). Click any chart to open full-size.

Strongest outcomes (what HH_HL_STREAK looks like when it works)
Weakest outcomes (what HH_HL_STREAK looks like when it fails)
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 % (spx) Bench % (spx) Alpha % (spx) p (HAC) Stock % (msci) Bench % (msci) Alpha % (msci) p (HAC) Stock % (spxew) Bench % (spxew) Alpha % (spxew) p (HAC)
Trending + Low vol Clean directional grind, low whipsaw 10,942 -0.00% +0.59% -0.56% <0.001 -0.00% +0.37% -0.35% <0.001 -0.00% +0.14% -0.13% 0.0460
Trending + High vol Crisis selloff or parabolic rally 73,497 +1.20% +1.21% +0.03% 0.6053 +1.20% +1.08% +0.14% 0.0133 +1.20% +0.90% +0.30% <0.001
Non-trending + Low vol Quiet chop, summer doldrums 20,218 +0.10% +0.77% -0.63% <0.001 +0.10% +0.58% -0.45% <0.001 +0.10% +0.42% -0.28% <0.001
Non-trending + High vol Classical "whipsaw zone" for momentum 114,054 +1.15% +1.21% +0.00% 0.9901 +1.15% +1.21% +0.05% 0.2438 +1.15% +1.16% +0.09% 0.0494
Sub-period breakdown table (20d alpha)
Historical clustering check. If alpha concentrates in one era, the signal's robustness is questionable.
Period N Alpha % (spx) p (HAC) Alpha % (msci) p (HAC) Alpha % (spxew) p (HAC)
2015-2019 2015-01-01 → 2020-01-01 54,803 -0.02% 0.6358 +0.17% 0.0004 +0.10% 0.0334
2020-2022 2020-01-01 → 2023-01-01 75,433 +0.12% 0.0349 +0.24% <0.001 -0.09% 0.0852
2023-2026 2023-01-01 → 2099-01-01 88,475 -0.30% <0.001 -0.30% <0.001 +0.27% <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: fraction of 200 random-date null iterations with mean ≥ observed. 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 zero edge even if the t-test says "significant."

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

Caution recommended. Bullish 20d alpha is -0.28% and worse than random — triggering on random dates would have produced better long-side returns. Either direction fails the "beats random" test. Don't use Highs/Lows streak as a standalone entry trigger. It may still be useful as part of a composite (section 4).

2 · When it works — the setups that drive it

  • Best bullish setup: Non-trending + High vol — alpha -0.07% / 20d on 124,133 historical triggers.
  • Best bearish setup: Trending + High vol — alpha +0.03% / 20d on 73,497 historical triggers.
  • Best era for bullish: 2020-2022 — alpha +0.04% / 20d.
  • Best era for bearish: 2020-2022 — alpha +0.12% / 20d.

3 · When it fails — common false positives

  • Weakest bullish cell: Trending + Low vol — alpha -0.49% / 20d on 15,812 triggers.
  • Weakest bearish cell: Non-trending + Low vol — alpha -0.63% / 20d on 20,218 triggers.
  • Worst era for bullish: 2023-2026 — alpha -0.51% / 20d.
  • Worst era for bearish: 2023-2026 — alpha -0.30% / 20d.

Signal-specific failure patterns

Bullish streak signal fails strongly — the 'uptrend continuation' thesis doesn't work
Bullish HH/HL streak (N consecutive higher-highs-and-higher-lows) fires 245k bullish triggers. Average α=−0.28 at 20d (p(HAC)<1e-23, p_perm=1.000), deepening to −0.72 at 60d (p<1e-22). Extremely statistically significant failure — 245k triggers leaves no doubt. The late-stage 'momentum has persisted so it will continue' thesis does not survive the data.
evidence: bullish 20d α=−0.28 p_perm=1.000; 60d α=−0.72 p_perm=1.000
Bearish streak has modest but significant edge
Bearish HH/HL streak (consecutive lower-highs-and-lower-lows) at α=−0.10 at 20d (p(HAC)=0.002, p_perm=0.005), −0.22 at 60d. Smaller sample (218k) than bullish and smaller per-trigger alpha, but the permutation null agrees it's a real effect.
evidence: bearish 20d α=−0.10 p_perm=0.005; 60d α=−0.22 p_perm=0.005
2020-2022 flipped both directions — the noise period
Bullish 2020-2022 α=+0.04 (marginal positive), bearish 2020-2022 α=+0.12 (signal inverted). The COVID-era fundamentals broke trend signals. Outside that window the bearish side is consistent (2015-2019 α=−0.02, 2023-2026 α=−0.30).
evidence: bullish 2020-22 +0.04, bearish 2020-22 +0.12 — both lose sign

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. A multi-signal convergence backtest is planned but not yet run.

Trend-structure family

Higher-high / higher-low streak encodes the classical Dow-theory definition of an uptrend — a price structure of successively higher swing highs and swing lows (Dow theory as presented in Murphy, Technical Analysis of the Financial Markets, 1999; Edwards & Magee, Technical Analysis of Stock Trends, 11th ed. 2018). This overlaps with HH/HL structure, moving-average crossover, and long-term trend-break signals, which infer the same trend state from different measurements.

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.

  • Reverse-engineer the bullish thesisBullish streak fails because it fires late. A streak-RESET signal (first HH-HL after a downtrend break) might capture the bullish turn before it's extended. Separate signal design task.
  • Hold bearish trades the full 60d windowBearish alpha doubles from 20d to 60d. Time stops > profit stops.

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

5 · Before you act — 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 your size? If the trigger is on a $500M name and you want to move $1M notional, you're the tape. Consider adv20d ≥ 5% of your intended position.
  5. What invalidates you? Define a price level (for longs: a close below the trigger-day low; for shorts: close above the trigger-day high) and honor it. The backtest alpha is an average; any one trade can be at either tail.

Execution notes

Bearish side is the tradable direction. 60d compounds from −0.10 to −0.22 — holding through the full window captures more alpha. Entry open T+1. Bullish side is structurally broken on US large-caps 2015-2026 regardless of which sub-period you pick (except the COVID-era noise).