Inside the machines that run Wall Street now

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

Editor’s note: Some of the world’s most powerful businesses no longer rely on human instinct.

They rely on pattern recognition – systems that scan vast amounts of market data in search of repeatable setups with a statistical advantage.

This shift is already reshaping how money is made on Wall Street.

This is the idea that my colleague Keith Kaplan explores in the article below. He explains how his team built an AI-based system to detect recurring signals across thousands of stocks – and turn them into a simple, actionable strategy.

You can look through the full framework – and see the system in action – in its signal presentation, Available here.

“There is an entity that cannot be defeated.”

That’s how Lee Sedol – the world’s greatest Go player – described the AI ​​after losing a five-game competition against Google’s AlphaGo AI model in Seoul in March 2016.

The game of Go was invented in China more than 2,500 years ago. Two players place black and white stones on a grid, trying to capture each other’s pieces.

It seems easy. But it contains more possible positions than there are atoms in the observable universe. The best players win by feel and intuition rather than brute calculations.

So, Sedol thought he was safe. The game was too creative, too human, for a machine to hack. Before the match, he predicted that he would win every match.

Then came move 37 in the second half.

Google’s AlphaGo program has placed a stone in a position that no ordinary player could take – a move so bizarre that one commentator said: “It’s not a human move.”

He was right.

AlphaGo’s analysis showed that a human player would make this move less than 1 in 10,000 times. But that turned the tide in AlphaGo’s favor, and Sedol lost.

He lost the competition 4-1.

The machine couldn’t be smarter. But he can see patterns that the human eye cannot see. That was enough to defeat the best player in the world.

From boards going to the stock market

It’s a cautionary tale for investors today. AI models are much better at recognizing patterns now than they were a decade ago. There is no field richer in hidden patterns – or more efficient at rewarding those who discover them and punishing those who miss them – than the stock market.

That’s why my team and I Want Smith I’ve spent the last 12 months building a new AI application for self-directed investors like you.

He uses the same principles that defeated the world’s greatest Go player to discover patterns that indicate the most promising trades of the day – 90 minutes before They happen.

I’ll show you how it works today – and I’ll pass along the link where you can see it in action. First, let me give you some background on TradeSmith and what we all do.