bullish_trend_breakdown
Bullish Trend Breakdown
Reverse of Bearish Trend Breakout. Identifies stocks in a long-term uptrend that are breaking down short-term, confirmed by a 20-day new low. Triggers when price is below the Nth percentile of the short range AND above the Nth percentile of the long range AND makes a new N-day low.
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 |
|---|---|---|---|
| short_months | Short range (calendar months) | 3 | 1–6 |
| short_percentile | Short range percentile | 20 | 1–50 |
| long_years | Long range (calendar years) | 5 | 2–10 |
| long_percentile | Long range percentile | 75 | 50–99 |
| breakdown_period | New low lookback (days) | 20 | 5–60 |
Historical context
86,514 triggers on 9,436 tickers, 2004-02-11 → 2026-05-01. Universe: US large-cap (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, US-only
Holding-period sensitivity. Bullish columns: positive = signal worked (long the trigger beat the index). Bearish columns: negative = signal worked (the flagged stock underperformed).
| Horizon | Bearish α |
|---|---|
| 5-day | +0.14% |
| 20-day | +0.27% |
| 60-day | +0.72% |
| 1-year | +3.60% |
Bullish Trend Breakdown is a single-direction signal — only the bearish side is meaningful.
Where does BULLISH_TREND_BREAKDOWN 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.
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. The 20d alpha you'd actually capture if you took the trade. Bars matching your direction's "right" sign (green) = the signal worked in that regime; opposite sign = avoid it there. A signal with one strong-positive bar and three flat ones isn't a "20d alpha" signal — it's a "20d alpha when the stock is X" signal.
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 matching your direction's "right" sign = the signal is durable. One era doing all the work = a regime-specific edge that may not repeat. The bigger the variance across eras, the smaller the position you should run. Long-history signal: requires 1260 trading days of prior data per ticker. The earliest era may show fewer triggers as a result.
Longer-horizon views
This signal carries a long lookback window (1260 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 so you can see how the signal's relationship with the benchmark evolves with holding period.
60-day alpha by stock regime
60-day alpha by era
1-year alpha by stock regime
1-year alpha by era
1-year observed alpha vs random-date null
↓ Bearish triggers negative alpha = signal was right (stock underperformed market)
| Bench | Metric | 1d | 5d | 20d | 60d | 252d |
|---|---|---|---|---|---|---|
| spx | Stock % | -0.01% | +0.40% | +1.35% | +3.16% | +10.50% |
| Bench % | +0.01% | +0.38% | +1.43% | +3.28% | +11.88% | |
| Alpha % | -0.02% | +0.03% | -0.13% | -0.13% | -1.31% | |
| Median alpha | -0.03% | -0.06% | -0.56% | -1.54% | -6.54% | |
| Hit rate (α>0) | 49.2% | 49.2% | 46.3% | 44.8% | 40.2% | |
| p (naive) | 0.0191 | 0.0460 | <0.001 | 0.0172 | <0.001 | |
| p (HAC) | 0.0188 | 0.1043 | 0.0052 | 0.3020 | 0.0719 | |
| N | 84,265 | 81,344 | 80,322 | 77,138 | 66,818 | |
| msci | Stock % | -0.01% | +0.40% | +1.35% | +3.16% | +10.50% |
| Bench % | -0.01% | +0.34% | +1.28% | +3.03% | +10.46% | |
| Alpha % | -0.00% | +0.08% | -0.03% | +0.19% | -0.09% | |
| Median alpha | -0.04% | -0.03% | -0.49% | -1.22% | -5.47% | |
| Hit rate (α>0) | 49.0% | 49.6% | 46.9% | 45.7% | 41.7% | |
| p (naive) | 0.8972 | <0.001 | 0.2359 | 0.0004 | 0.5287 | |
| p (HAC) | 0.8979 | <0.001 | 0.4670 | 0.1281 | 0.8983 | |
| N | 83,528 | 80,467 | 78,663 | 76,044 | 66,383 | |
| spxew | Stock % | -0.01% | +0.40% | +1.35% | +3.16% | +10.50% |
| Bench % | -0.00% | +0.28% | +0.98% | +2.46% | +6.91% | |
| Alpha % | -0.00% | +0.14% | +0.27% | +0.72% | +3.60% | |
| Median alpha | -0.04% | +0.02% | -0.14% | -0.66% | -2.48% | |
| Hit rate (α>0) | 49.0% | 50.2% | 49.1% | 47.6% | 45.9% | |
| p (naive) | 0.7007 | <0.001 | <0.001 | <0.001 | <0.001 | |
| p (HAC) | 0.7020 | <0.001 | <0.001 | <0.001 | <0.001 | |
| N | 83,683 | 80,947 | 79,588 | 76,515 | 66,659 |
Permutation null detail — all horizons × both benchmarks
| Horizon | Bench | Observed lift | Null mean | Null 95% CI | pperm |
|---|---|---|---|---|---|
| 1d | spx | +0.06% | +0.06% | [+0.04%, +0.07%] | 0.781 |
| 1d | msci | +0.11% | +0.06% | [+0.05%, +0.08%] | 1.000 |
| 1d | spxew | +0.10% | +0.05% | [+0.03%, +0.06%] | 1.000 |
| 5d | spx | +0.24% | +0.23% | [+0.19%, +0.26%] | 0.701 |
| 5d | msci | +0.29% | +0.23% | [+0.20%, +0.27%] | 1.000 |
| 5d | spxew | +0.31% | +0.21% | [+0.17%, +0.25%] | 1.000 |
| 20d | spx | +0.40% | +0.72% | [+0.65%, +0.78%] | 0.005 |
| 20d | msci | +0.37% | +0.72% | [+0.66%, +0.79%] | 0.005 |
| 20d | spxew | +0.56% | +0.67% | [+0.61%, +0.73%] | 0.005 |
| 60d | spx | +0.75% | +1.60% | [+1.49%, +1.71%] | 0.005 |
| 60d | msci | +0.63% | +1.61% | [+1.50%, +1.73%] | 0.005 |
| 60d | spxew | +0.88% | +1.53% | [+1.42%, +1.64%] | 0.005 |
| 252d | spx | -1.19% | +3.55% | [+3.33%, +3.76%] | 0.005 |
| 252d | msci | -2.36% | +3.48% | [+3.25%, +3.69%] | 0.005 |
| 252d | spxew | -0.38% | +3.12% | [+2.92%, +3.35%] | 0.005 |
Example triggers on US large-caps (2023+, mcap ≥ $30B)
Six recent bearish BULLISH_TREND_BREAKDOWN triggers on US mega-caps. Top three: the signal's best outcomes. Bottom three: the worst. Catalyst-driven outliers (|α| > 25%) excluded so what's left is the signal's own typical good and bad days, not earnings shocks.
Strongest outcomes (what BULLISH_TREND_BREAKDOWN looks like when it works)
Weakest outcomes (what BULLISH_TREND_BREAKDOWN looks like when it fails)
Stock-regime quadrants (2×2 per-stock, 20d alpha detail table)
| 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 | 10,681 | +0.53% | +1.46% | -0.91% | <0.001 | +0.53% | +1.17% | -0.76% | <0.001 | +0.53% | +0.88% | -0.44% | 0.0023 |
| Trending + High vol Crisis selloff or parabolic rally | 16,539 | +1.84% | +1.66% | +0.14% | 0.1967 | +1.84% | +1.46% | +0.28% | 0.0085 | +1.84% | +1.16% | +0.58% | <0.001 |
| Non-trending + Low vol Quiet chop, summer doldrums | 15,988 | +0.57% | +1.12% | -0.54% | <0.001 | +0.57% | +1.05% | -0.48% | <0.001 | +0.57% | +0.76% | -0.19% | 0.0175 |
| Non-trending + High vol Classical "whipsaw zone" for momentum | 43,306 | +1.65% | +1.48% | +0.11% | 0.0928 | +1.65% | +1.32% | +0.20% | 0.0020 | +1.65% | +1.03% | +0.49% | <0.001 |
Sub-period breakdown table (20d alpha)
| Period | N | Alpha % (spx) | p (HAC) | Alpha % (msci) | p (HAC) | Alpha % (spxew) | p (HAC) |
|---|---|---|---|---|---|---|---|
| 2015-2019 2015-01-01 → 2020-01-01 | 142 | +0.87% | 0.4439 | +0.94% | 0.4270 | +0.89% | 0.4691 |
| 2020-2022 2020-01-01 → 2023-01-01 | 27,103 | -0.13% | 0.1188 | +0.04% | 0.6345 | -0.26% | 0.0024 |
| 2023-2026 2023-01-01 → 2099-01-01 | 59,246 | -0.13% | 0.0232 | -0.07% | 0.2384 | +0.51% | <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
Neutral signal. Bullish 20d alpha —, bearish -0.13%. Neither direction beats random date selection (pperm not significant either way). Observed alpha is likely noise or universe drift rather than information about the trigger. Useful for context, not for standalone entries.
2 · When it works — the setups that drive it
- Best bearish setup: Trending + High vol — alpha +0.14% / 20d on 16,539 historical triggers.
- Best era for bearish: 2015-2019 — alpha +0.87% / 20d.
3 · When it fails — common false positives
- Weakest bearish cell: Trending + Low vol — alpha -0.91% / 20d on 10,681 triggers.
- Worst era for bearish: 2020-2022 — alpha -0.13% / 20d.
Signal-specific failure patterns
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.
No classical-TA family-redundancy claim applies to this signal. Pairing behaviour is a backtest question and has not been measured yet.
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.
- Use as a filter to gate out bullish signals — The most useful application: if bullish_trend_breakdown has fired in the last 20d, SKIP all bullish momentum signals on that stock. Filter application; no trading P&L of its own.
- Wait for more data — With only ~6 years of meaningful history (2020+), the signal's base rates are uncertain. Another 5 years of observation will clarify whether this is a reliable regime-change indicator.
See also Why technical-only signals don't survive on their own for the broader argument.
5 · Before you act — a 5-point checklist
- 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.
- 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.
- 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.
- 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.
- 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
Use as a REGIME SIGNAL, not a trade entry. When bullish trend breakdown fires on a stock, that stock shifts from 'in a long-term uptrend' to 'regime uncertain' — which should gate OUT bullish trades rather than trigger bearish trades. Entry open T+1 if traded directly. 60d horizon is where the alpha is most meaningful; 20d is marginal.