This website uses cookies
Read our Privacy policy and Terms of use for more information.
Four proprietary models score about a hundred markets overnight. The names they agree on become the portfolio, up to ten at a time, before the US open.
Built by Yimin Xu, former G10 rates market-maker at NatWest Markets.
Cash is a position here, not a leftover.
Three names sit exactly on the 15% cap. Sizing wanted to give them more.
QQQ is long on the signals page and still not held. Only two of the four agree.
Every morning, in the same shape, whatever the week is doing.
All four are simulated on Macro & Megacaps, net of costs, on data the models never saw. The live record starts 3 August 2026 and publishes every week.
From $3,000 a year, with a free first month on every annual plan.
Picking the names is the easy part. The sizing, the timing and the exit decide the year, and all three are settled by rule before the open.
If none of those is you, the free month answers the rest.
We approach the markets with an unfiltered, independent mindset. We constantly back test theories and popular claims, and always seek to improve our process along the way.
When our discretionary view differs from that of the systematic, we explicitly highlight so. We never muddle the two. Over time, We have found that a systematic process is invaluable to market clarity and investor psychology.
Everything published is locked when it goes out and cannot be edited later. Downgrades publish the week they happen, the ones that did not work included.
Read it free for a month. Cancel inside the month and pay nothing.
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.
Nothing here tells anyone what to do with their money. This is the operation I run for my own investing, published as I use it, including the weeks it goes badly.
The work is closer to observation than prediction. The models report where the market stands, the record shows what came of it, and the process improves as that evidence builds. None of it asks anyone to be attached to a particular trade, mine included. We are watching the market from the same side of the glass.