We never touch your money. We built the risk desk the institutions keep for themselves — and handed it to you. Real market risk in real time, the sectors and themes trending up and down, a daily focus setup, and your portfolio graded on demand. The kind of institutional risk desk that usually costs 1–3% of your assets a year — offered here for a flat monthly subscription. Built by us, for us, shared with you.
We rode markets over the edge like everyone else — fully invested at the top, reading about the regime change in the news, after the fall. The institutions? They got the phone call. They had risk desks. We had headlines and hope.
So we built what we couldn't buy: a macro engine that scores the whole economy into one regime read, a set of crisis tripwires, and a scoring core that grades every stock on momentum and exhaustion — the pillar designed to fire before a breakdown shows in price.
It worked well enough that keeping it to ourselves felt wrong. Retail can't afford institutional protection — so we priced ours like a streaming subscription and published the entire architecture. No black box. No guru. Just the machine, daily.
Our macro engine scores the whole economy into one number, and that number commands an 8-rung ladder — how much risk the models are allowed to carry. Here it is recomputed across 604 months of history, laid against the S&P 500. Shaded columns are the market's real peak-to-trough decline around each recession. One question: what was the machine saying while the market was topping — and what would listening have saved you?
In 2008 the S&P 500 lost 57% in one of the worst recessions on record. The EMP engine saw the stress building and stepped the models down — Take Profits at the October top, walked to Full Defensive before Lehman. A portfolio following that prescribed exposure would have fallen just 7%: a 50-percentage-point swing. And it isn't a one-off — across six recessions since 1980, an average 34% market decline came out as 11% at the machine's own exposure. Hypothetical model performance.
Volcker's rate shock. Before the market turned, EMP was already at Full Defensive — a tenth invested. The decline happened almost entirely without you.
The double-dip. Full Defensive at the peak and defensive for twenty months. A 27% index decline came out as a 2% scratch.
Oil shock and credit stress. Sell Alert at the top — a quarter invested — so the drawdown landed on a book already mostly in cash.
Sell Alert in March 2000 while the crowd bought the dip — and nearly perfect through March 2002. Then the recovery gate began flipping monthly: a credit-data gap had disarmed the guard that should have stopped it.
The best call in the record. Take Profits at the October 2007 top, walking down to Full Defensive before Lehman. The index lost 57%. The machine's path lost 7%.
The honest one. At the February 19 peak EMP said Build Risk — fully invested. A pandemic is not in macro data. It cut hard afterward, but it reacted; it did not warn. You would have felt nearly the whole crash.
Alongside the EMP regime engine above, our recession engine collapses the credit cycle, the yield curve, the labor market and the housing pipeline into one number: the probability of a U.S. (NBER) recession beginning within twelve months. Here it is recomputed across every month since 1968, laid against the S&P 500. Shaded columns are the NBER recessions. One question: what was the model saying while the market was still climbing — and how much warning would listening have bought you?
Our recession-probability panel flagged 7 of the last 8 U.S. recessions before they began — its probability pushed above the 50% line a median of ten months ahead of onset, at an average peak of 89%. The lone miss was 2020: a pandemic is invisible to macro data, and the model topped out at 48% the month before lockdowns.
The model climbed out of the teens through late 1969 and breached 50% in November — two months before the downturn began — dipping briefly in December before surging as the recession took hold. A tight but correct call at the very start of the data.
Flat near 2% through the spring, then a vertical ramp as the curve inverted and permits rolled over: 65% by July, 85% by August, 94% by October — four months of warning before the November 1973 onset.
Volcker's first squeeze. The probability was above 50% from March 1979 and pinned near 99% for months before the January 1980 onset — ten months of warning.
The messy one. The model stayed 90–100% through the 1980 recession, cooled in the gap between the dips, re-fired to 66% in September 1980 and 98% by November, eased into the 20s–30s that spring, then jumped back to 80% in July 1981 — the month the second dip began.
Flagged early — above 50% from April 1989 into early 1990 — then dipped in the spring before re-surging to 78% in June 1990, the month before the oil-price spike tipped the economy over.
Crossed 50% in April 2000 as the curve inverted and hit 96% by that November — eleven months before the recession began in March 2001.
First crossed 50% in November 2006, then from January 2007 held 85–97% through the entire year — thirteen months of elevated warning before the December 2007 onset of the deepest recession in the sample.
The one it could not see. Macro inputs were benign into 2020; the probability peaked at 48% in February, the month before lockdowns. No model built on slow-moving economic data can forecast a pandemic — shown here in full candor.
This is the actual risk read from our July 8, 2026 Sample Brief — where the danger sits right now: the macro regime, live crisis tripwires, and the odds of recession. It's a frozen sample. Members get this rebuilt with today's data, every trading day before the open.
One direction, four stages: the economy gets scored before a single ticker is considered, and every stock gets graded inside that weather.
Edge Market Pulse scores the economy across a broad macro panel and prints one of 8 regime bands.
The regime becomes a risk budget: how much invested, how much cash — before any stock picking.
One trusted snapshot: the full universe, a battery of technical signals per name, hard gates against stale data.
Two selection models — disciplined and conviction — fill the budget with individually scored names.
Trend, volume expansion, slope structure. Finds the strong names — entry quality.
Relative strength, 52-week position and theme-relative return. Ranks a name inside its cohort — leaders over laggards.
The early-warning pillar, built to fire before the breakdown shows in price. Downside protection isn't a slogan here; it's a third of the score.
The complete architecture — EMP, PAM, BSM, the CRC scoring core, and both selection models. We published the blueprint because trust is earned with transparency, not slogans.
Inspect the machine →A complete Daily Brief from a live run — regime gauge, clickable sector drill-downs, risk posture, earnings radar, and the Post Studio. Judge the product by the product.
Click around in it →Free Weekly Radar forever, or the full Daily Brief for less than a streaming bundle. Founding-member pricing locked for life for the first 100 subscribers.
Compare plans →Run your own holdings through our machine: a personal CRC grade, exhaustion flags, regime fit, and a shareable scorecard. Private by design — your book never leaves your browser.
Scan my portfolio →Who we are, why the name, and every disclosure in plain sight — including how AI assists our writing and why our model results are labeled hypothetical. Honesty is the moat.
Read the fine print →The pipeline was built to protect our own money, and it still does — every score you read is one we act on ourselves. Alignment, disclosed.
Every stage, every pillar, every guardrail is documented on The System page. If a research shop won't show you the machine, ask why.
Scores are dated, archived, and never quietly rewritten. A warning system you can't audit is just marketing. See the record →
Impersonal model output, plain-English narration, and disclaimers on every page. We'd rather under-promise than manage your disappointment.
Start free. Read the radar for a while. Upgrade when it earns your trust — that's the only way we'd want it.
Want proof before you even sign up? Join free to read the Weekly Radar →