Today was one of the ugliest days the Nasdaq has seen in a long time. Even though we’ve been fully out of the market for a while, we thought it was worth sharing our view of what’s happening. Days like this are uncommon, and they give us some very interesting readings on the data we follow. Sorry to sound a bit excited here, but I guess volcanologists get embarrassingly excited when there’s a massive eruption… For us, a red day of this magnitude is telling. What had so far be

-------------------------------------------------- Update no 1 on Nov. 5th -------------------------------------------------- Today, the whole market sold off hard. QQQ fell 6.5% and SPY dropped 4.4%. This was not a crypto story: investors pulled money out of almost everything at once, and a wave that size was always going to catch Bitcoin too, which fell 5.5%. That pullback was strong enough for our Active Hodling signal to trigger a WU Out flag, only a day after yesterday's

Good afternoon, folks, As everybody knows, our hedge signal has been on for a while now, and it isn’t ready to give us the green light yet. Friday was a very bad day for the market, with QQQ down close to 4.5% at its worst point. But we do see a few things unfolding, and we thought a quick market update was worth it. So here it is.

When we launched PAND·AI in December last year, we mentioned that it was bound to evolve in its first year. Part of that was about gathering your feedback, which was indeed helpful, especially in the first few months after launch when we fixed some quirks in the setup. The other part was due to seeing how fast AI models were improving at the time. Almost a year later, we can confirm that they improved even faster than anyone expected. The models today can reason more carefull

----------------------------------------------------

Some of you saw an On Margin flag today on the TradingView chart of our Margin Risk Indicator. That flag is not valid, and you should not act on it. If you follow the signals on the DataHub, you will not have seen it at all: we kept it off the DataHub on purpose to avoid any confusion.

----------------------------------------------------

With today's close $44 under our threshold, our Active Hodling signal triggered a WU Out flag. In the current cyclical downtrend phase (yellow background), the strategy is biased towards being out of the market and will exit on any sign of momentum loss or reversal. This is exactly what happened here. After Sunday's $86K close, we have seen a sequence of four red days that brought Bitcoin back down to $81K, which provided sufficient downward momentum to reach our threshold. A

On Thursday, Vincent sent an update explaining why some of you may have seen a WU Out on the Hedging Signal in TradingView and why it was NOT a valid signal. In the blog post, Vincent explained that during our rework of the Market Breadth indicator we discovered that one dataset inside the indicator has started misbehaving. If you have not read it already, you may start there as it gives some insight on why the work we did here matters. For the rest, this blog post is the ful

Dear Folks. Today, an hour after the close, when the new data became available, our market breadth-related indicator triggered an exit on our Hedge strategy. We didn’t send an SMS about it, as we consider it not valid. This has nothing to do with our subjective interpretation but is rather based on scientific evidence we discovered while working on our new Hedge algorithm.

---------------------------------------------------------

As part of the rework of our hedge signal that began this summer, our first step was to take a closer look at the bear-market component. Vincent already touched on this in the project explanation blog post, but for the sake of completeness, here is a short reminder of how it works. Our hedge signal operates in two distinct modes. In their original work, Jennifer and Vincent found that the “standard” metrics used by the strategy did not perform reliably during bear markets. B

Hi folks, In my traditional year-end post eight months ago, I mentioned that one of our goals for this year was to improve our hedge algorithm. That work is now well underway. We’ve been working on it for the past few weeks and are finally ready to release the first part of what we’ve done. But before diving into the more technical details and the changes we are making, I thought it would be useful to first revisit why we decided to rework what is, after all, one of the core

For the past month and a half, Bitcoin did almost nothing. Price drifted in a narrow band, day after day, and by some measures this was the quietest stretch in the asset's entire history. Volatility this compressed is rare, and it never lasts forever. We were actually preparing an update on this last week. Vincent ran an analysis on the compression and the honest conclusion was that there was no guiding pattern forming at that point. Similar squeezes in the past have resolved

Yesterday, the Margin Risk Signal flipped back to On Margin. The short version: we are bringing the model portfolio to 100% invested, through QQQ, and we are stopping there. No borrowed money, no leverage this time. The rest of this post explains both halves of that decision. In our last post, we described a market that was consolidating without showing a clear trend. The data simply was not leaning far enough in either direction to call it a meaningful shift. Since then,

After our last post on June 10th, where we detailed why we added a new position to our portfolio, QQQ rallied a further 7% in a matter of days. Since then, the market has spent a full month consolidating without establishing any real trend.

Today we added a 24% QQQ allocation to our portfolio, bringing our total equity exposure to 75%. We are currently between signals, and positions taken in these periods are by nature more subjective. They rest on one's read of the situation rather than on a hard, backtested trigger. They don't carry the same statistical weight as a Hedge Signal call, and we'd encourage you to treat them accordingly. Here is our read, briefly.

Today, we're taking a small pause on the data analysis in order to deliver our first major DataHub update since its launch. The original scope of this update was to add detailed descriptions in a new popup window and other small fixes. It then grew into a complete re-styling of the DataHub, a new home page, a new guide page and many more small improvements that I will go into in this blog post.

Hi folks, It’s been a while since I last wrote anything. I had to leave the boat under Zackary’s captainship, not because of a lack of interest, but because I became overloaded in a way I had never anticipated. My new role as CTO AI at Robotiq came at a moment when Physical AI is exploding, adding another layer on top of everything else. At first, it was manageable. I was still able to post several times in January and into early March. But after a few back-to-back busines

We just received a WU Out signal only 15 days after the latest one and 8 days since the latest WU In. This quick signal succession is rare in the Active Hodling signal history, but not unexpected. A rally during the decline phase (yellow background) of the strategy marks the frontier between a bear market rally and the start of a new bull market. As the strategy turns more defensive in this phase, a momentum reversal during a rally will promptly trigger a WU Out signal defaul