AI Trading Signals Are Solving the Market’s Data Problem

Listen to the audio version of this article (generated by AI).

Editor’s Note: Most investors are staring at the same data… and missing the same signals.

They’re buried in price action, timing, volatility, and dozens of other factors — and consistently show up before major moves.

The challenge has always been finding them. 

That’s where AI is starting to change the game.

In the guest essay below, Keith Kaplan shares how his team is using it to surface hidden market signals — the same kind of pattern recognition that powered some of the most successful hedge funds ever.

You can see exactly how it works — and what it’s finding right now — in his Signals presentation.

Tycho Brahe’s mission in life was to be the first to explain how the planets really moved.

So this obsessive 16th century Danish astronomer spent more than two decades building the most precise record of planetary motion the world had ever seen — and then guarded it so jealously almost no one was allowed to see it.

In Brahe’s time, there were no telescopes. Every measurement he took was with the naked eye, using instruments he designed and built himself on a small island off the coast of Denmark.

It was a data set unlike anything that had ever existed — page after page of handwritten figures and precise planetary positions.

He couldn’t interpret all that data alone. So he brought on a brilliant young German mathematician named Johannes Kepler. But Brahe, afraid Kepler might make the discovery first, handed his apprentice only just enough data to be useful and locked the rest away.

That arrangement lasted barely a year. In October 1601, Brahe died suddenly. Kepler inherited his notebooks and studied them intensely for the next four years.  

What he found was proof that everything astronomers had assumed since ancient Greece was wrong. 

Kepler realized that planets didn’t move in perfect circles. They moved in ellipses — slightly flattened ovals, with the sun off to one side rather than in the direct center. 

Almost a century later, Isaac Newton read Kepler’s laws of elliptical motion and worked out the force that explained them. He called it gravity.

One of the most important ideas in the history of science was hiding in Brahe’s notebooks for decades. The data had always been there. All it needed was someone who could make it legible.

From Hidden Data to Actionable Signals

I’m telling you this because the stock market has a Tycho Brahe problem, too.

It generates more data in a single trading day than Brahe recorded in a lifetime. The problem is, for most of its existence, only a tiny fraction of it has been readable.

But today, thanks to AI, it’s possible to find “signals” inside that data — repeating patterns that point to future moves in stocks, many with historical accuracy rates of 90% or better.

I know because my team and I at TradeSmith have created a new AI-powered trading tool that’s unearthed more than 200 of these signals across nearly 2,500 stocks.

As I showed the nearly 9,000 people who joined my AI Signals Trading Event on Wednesday, in a six-year backtest, a model portfolio of these signals trades delivered a 12x return. 

And in 2022 — the worst year for stocks in half a century — they produced an average backtested gain of 16.6% while the S&P 500 fell nearly 20%.

If you missed it, the replay is still online. It’s packed full of trade examples, strategy details, and on-screen demos. Go here to watch it now.

Today, I want to share something I didn’t have time to cover on Wednesday — how much work and ingenuity went into building our new system.

The answer is: more than I expected.

The ‘Paris Weather’ Insight That Changed Everything

Our chief developer, Mike Carr, has been writing code for 40 years.

He spent 20 years in the U.S. Air Force – coding nuclear missile paths, working on cryptography for the National Security Agency, and helping install an early version of the internet at the Pentagon.

When he left the military, he went on to manage more than $200 million in client funds. He also became a Chartered Market Technician — a credential only about 4,500 people in the world hold. 

Two years ago, he joined TradeSmith to help us develop new analytics and strategies. And he brought with him the kernel of an idea he’d been working on for more than 20 years.

In 2003, Mike started doing rudimentary signal studies. Every time he spotted a repeating pattern in the data that tended to precede a move in a stock — he noted it down. He traded this way for years, constantly testing what worked and what didn’t. 

Then in 2016, he read a Bloomberg profile of Jim Simons’ storied hedge fund, Renaissance Technologies. One detail stuck with him: Simons had once found a tradable signal involving the weather in Paris.

If he could find a signal in Paris weather, Mike realized, the signals hiding in ordinary market data had to be almost limitless. That was the moment he decided to stop hunting for signals manually and start building a system that could hunt them at scale — one ordinary investors could actually use.

Last year, we started feeding the 150 or so signals he’d collected into an AI system and prompted it to generate more like them. We processed more than 1 trillion database rows, running every stock through 847 individual calculations. We tested every combination of price patterns, technical indicators, and calendar conditions we could find.

The Problem With Too Many Trading Signals

Then we hit a problem we hadn’t anticipated.

On any given day, our AI-powered signals generator was delivering a flood of 697 trade setups – all with historical accuracy rates of 75% or better. It was far too much for any trader to handle, no matter their level of experience. 

So we spent the next six months solving a different problem: How do you take that many high-quality signals and deliver something an investor can actually use?

The answer Mike came up with was the Quality Score. It’s a 0-to-100 rating that factors each signal’s win rate and average returns and uses machine learning to figure out how effective it was during similar market conditions in the past. 

Pair that with a focused model portfolio, and the flood became an actionable shortlist.