One portfolio covers the whole map: macro, megacaps, crypto and the rails behind it.
It runs across 70+ names, and deliberately not one asset class.
- US indices, rates, the dollar, credit and the sector ETFs
- The Magnificent 7, plus the 40 megacaps driving AI
- Crypto and crypto-adjacent indices
Four proprietary models read every one of them before the US open, and the portfolio that comes out holds ten names or fewer with an exact weight on each. How It Works explains the machinery.
The whole list, published. Every name here is scored every morning, and nothing is covered occasionally or "when it looks interesting". New tickers are added every month, and the list only ever grows.
73 names, one portfolio. Additions are included at no extra cost. The price is locked, the universe is not.
Not just the signals, the portfolio I run off them, published every Monday
Turning signals into a portfolio is where most people give up, so we publish our answer: a plain list of tickers and weights every Monday, drawn from the 73 names covered here.
- It can never contradict the signals you paid for. The rule is enforced in code, not by intention.
- Thin convictions never make it in. At least three of the four models have to back the call, as a simple count.
- Membership is sticky. A holding still long and still inside the top 15 keeps its place, and at most two new names arrive each week. New entrants are picked by rank minus their correlation to what is already held.
- One position can never take over. A volatile name gets a smaller slice, and a cap sits on top: 15% at ten holdings, 25% ever.
- It steps back before anyone has to be brave. The invested share is scaled so risk lands at or below the index, on schedule. This is an aim, never a promise.
- Rebuilt weekly, exited daily. Weight drifts under 5% are left alone in between. A holding goes the same day its record turns flat, or the day fewer than three of the four still agree. Long only, unlevered, 5 basis points per side.
Ten years of testing, on data the models had never seen.
Every point used only the data available on that day. It is the same construction that runs live, run backwards over history, with 5 basis points per side already taken out.
Simulated results. Long only, unlevered, gross capped at 1.0, net of 5 bps per side. Past simulated performance is not indicative of future returns and this is not investment advice.
Two portfolios that rarely have a bad spell at the same time.
Macro & Megacaps and Commodities share exactly the same construction. What differs is the universe underneath them. Equities and the commodity complex are driven by different things, and often in opposite directions: supply, inventory and the dollar on one side, risk appetite and earnings on the other.
The second portfolio earns its keep on the days the first is having its worst week. In 2022 the commodities portfolio rose 19.6% while the index fell 18.7%.
| Simulated, 2022 | Return | Volatility | Sharpe | Worst drawdown |
|---|---|---|---|---|
| The index (SPY) | −18.67% | 24.1% | −0.74 | −26.29% |
| Macro & Megacaps alone | −12.80% | 14.6% | −0.87 | −16.17% |
| Blend, 75 Macro & Megacaps / 25 Commodities | −4.70% | 13.1% | −0.30 | −10.05% |
| Commodities alone | +19.60% | 16.7% | +1.16 | −11.48% |
Carrying a quarter of it turned a 12.8% loss into a 4.7% one, and cut the worst fall along the way from 26.29% to 10.05%. A year like 2022 is where a second portfolio either earns its place or does not.
Neither portfolio is short anything, so this is not a hedge in the strict sense. The blend still lost money in 2022, and a fall that takes everything down together will take this down too. Both scale back into cash, which is how each one dials its own risk. What the pairing adds is less correlation between two long-only portfolios, and that shows up as a shallower worst drawdown rather than as outright protection.
Simulated. Macro & Megacaps 75, Commodities 25, rebalanced on the first session of each year and left to drift in between. Long only, unlevered, net of 5 bps per side. Sharpe uses daily returns at a zero risk-free rate, and the drawdown is measured inside the calendar year. Past simulated performance is not indicative of future returns and this is not investment advice.
One service at two depths, and a companion portfolio beside it.
Both tiers cover the same 70+ names and the same portfolio. What changes is how much writing comes with it. The first question is how deep to go here, the second is whether Commodities earns a place beside it.
Macro & Megacaps: Signals
The models, the portfolio, every morning.
Four models read every name before the US open, and build the portfolio from what they agree on.
- Daily signals on 70+ names, before the US open
- The portfolio: tickers and target weights, weekly
- Ten years of testing on data the models never saw
Macro & Megacaps: Signals & Research
A bad month is therefore never a surprise.
The portfolio will hold something through a bad stretch. Whether you stay with it depends on whether you saw it coming.
- Everything in Signals, in full
- The macro note, twice a week: the Fed path, the curve, then the indices, the Mag-7, metals and crypto
- Deep dives on the names the portfolio holds: the business, the numbers, the valuation and what would drop it
Commodities: Signals
A companion portfolio for the parts of the cycle equities find hard.
24 names across metals, energy, agriculture and uranium, plus the producers. It runs the same method on a separate universe.
- Daily signals on 24 names, before the US open
- The commodities portfolio, weekly
- Ten years of testing on data the models never saw
- A third off beside either Macro & Megacaps tier
Every subscription includes its portfolio at no extra cost, and your price is locked for as long as you stay. Prices exclude VAT.
Read a month of it before you decide anything.
Annual plans carry a free first month. You get the Macro & Megacaps page exactly as I read it: the four models each morning, the portfolio they build, and the record that says afterwards what came of it. Cancel in-month and pay nothing.
The work is closer to observation than prediction. None of it asks you to be attached to a particular trade, mine included. The market is the thing being read, and we are watching it from the same side of the glass.
Published for information and education. It is not personalised advice, not a managed account, and not a recommendation to buy or sell any security. Capital is at risk, and past and simulated performance tell you nothing certain about the future.