How it works

Patient signals. Clear logic.

EdgeBeacon is a rules-based alert engine. It monitors the market continuously and stays silent until its proprietary market and company-level checks align. When they do, it surfaces the highest-conviction candidates.

61.2%

S&P 500 Top-5 beat SPY at 60d

Backtest n=420 · OOS 53.6% (n=192) · 95% CI 54.0% to 69.6% · 23 fear episodes

—

NASDAQ backtest retired

The previous NASDAQ claim was withdrawn and is not returning under the current structure.

—

Conviction lift retired

The previous conviction-lift claim was withdrawn and retired.

—

Avg-return under re-approval

Average-return evidence remains pending a separate owner decision.

Historical S&P 500 Top-5 backtest only: 61.2% beat SPY over 60 trading days (2020–2026, n=420); out-of-sample 2023+ was 53.6% (n=192); 95% CI 54.0%–69.6% across 23 fear episodes. Source: data/signal_quality_sp500_pit_totret_livegate.json. NASDAQ and conviction-lift claims are withdrawn and retired. Backtest, not a guarantee · Not investment advice.

Step 1

Read the market

EdgeBeacon doesn't run in every market. The engine stays dormant until a specific set of market-wide conditions reach a predefined threshold — a rare confluence that, by design, occurs only a handful of times in any given year.

All inputs must confirm: The gate is governed by our proprietary fear-regime threshold — multiple independent checks must align simultaneously. If any falls short, the gate stays closed. Partial fear isn't enough.
A secondary cross-check: A separate filter guards against false positives — distinguishing genuine market stress from routine pullbacks. The two checks are deliberately independent so neither can be overridden by the other.
Silence is the default: When conditions don't align, EdgeBeacon produces nothing. Long quiet stretches are part of the design. No signal is better than a forced one.

Step 2

Find the setup

With the market gate open, the engine scans hundreds of US equities for candidates with enough dislocation and confirmation to clear the full ruleset. Both must be present — dislocation alone is not enough.

Depth screen: A multi-week measure identifies stocks where selling pressure has reached historic extremes — the kind of sustained, extreme pressure that historically precedes stabilisation rather than continued decline.
Stabilisation filter: A separate confirmation layer reduces false positives before a stock is considered — distinguishing candidates that are stabilising from those still in decline. A candidate must clear both checks before it appears.
Fundamental quality: A point-in-time quality score — built only from data available on the signal date — distinguishes structurally sound companies from those that are cheap for a reason. Fundamentals act as a tiebreaker, not the primary screen.

Step 3

Rank by conviction

Multiple stocks can trigger on the same day. The engine scores each one on a predefined conviction model and surfaces only the highest-ranked setups — the ones with the strongest proprietary conviction profile.

Technical depth weighting: The primary input is a proprietary conviction score based on the depth and quality of the technical setup relative to historical norms. A setup that is deeply dislocated in a fear regime has historically outperformed one that barely clears the threshold.
Fundamental quality weighting: A point-in-time quality layer — built only from information available on the signal date — helps distinguish structurally sound candidates from those that may be discounted for good reason.
Top-5 per firing day: On active days the engine may identify more candidates than the product surfaces. EdgeBeacon shows a compact, conviction-ranked set. The prior conviction-lift claim has been withdrawn and retired.

The evidence

Historical evidence, narrowly republished.

Only the S&P 500 Top-5 60d beat-SPY claim above is approved for publication, with OOS, CI, episode count, source, and backtest framing attached. NASDAQ and conviction-lift claims are withdrawn and retired. Average-return and portfolio-overlay research remain under re-approval.

Case study · 2022 bear market

2022 had a large cluster of historical S&P 500 signals during a difficult market year. Specific per-trade and beat-SPY figures for that period remain withdrawn.

The honest trade-off.

EdgeBeacon is silent in calm markets by design. There are extended periods — sometimes more than a year — when the fear gate stays closed and the engine fires no signals at all. Following EdgeBeacon signals alone in those windows would have left you holding cash. That is the cost of regime discipline, and it is the right trade-off: the engine is designed as a complement to a core long-term allocation, not a replacement for one. When fear regimes do appear, EdgeBeacon surfaces the highest-ranked candidates only during those historically fearful windows.

How EdgeBeacon fits in a portfolio.

EdgeBeacon is designed to sit alongside a long-term core position in the broad market (e.g. an S&P 500 index fund), not to replace it. Most of the time the engine is quiet — it is built to surface candidates only when its proprietary checks align. Portfolio-level research is also under re-approval. Prior defensive-overlay proof points are temporarily withdrawn because their source fire set is being regenerated. Updated figures require a separate review before republication.

The honest summary: EdgeBeacon is an alert layer for patient investors who already hold an index core, not a market-replacement product.

Defensive overlay · backtested model portfolio

—

Defensive-overlay backtest

Under re-approval

—

Comparator

Under re-approval

—

Lift

No figure approved

—

Risk metrics

Under re-approval

Portfolio-overlay figures are temporarily withdrawn because their source fire set is being regenerated. Updated figures require a separate review before republication.

No portfolio-overlay number is approved for publication at this time. Historical results only.

This is a tool, not a guarantee.

The S&P 500 Top-5 60d beat-SPY claim above is approved. NASDAQ and conviction-lift claims are withdrawn and retired; average-return and portfolio-overlay research remain under re-approval. Past performance does not guarantee future results. EdgeBeacon surfaces long-only watchlist candidates only — it does not provide exits, position sizing, trade execution, or personalised recommendations. Position sizing, exits, and risk management remain entirely your responsibility. Not investment advice · Historical results only.