Trading is like skying. You always make the same simple moves (start, end, turn right, turn left) and the same tracks, but never in the same way. Never the same weather, snow condition, visibility, temperature, and so on: every time it’s different.
Imagine that the neural network knows the track. It does not guarantee that you arrive downhill integer, but it can avoid a lot of errors. Just the track, with slopes and boundaries and gradients all around. It has already descended that track and even some variants and similar. It can guide you. I should call the model r.Virgeel.
Now, in effect r.Virgeel knows also the condition of the snow, the visibility, the temperature and parameters, so it can even tell you that it’s better to stay home and sip a cordiale.
Mr. Market, as any good skier, will never do the same path twice, no matter how well r.Virgeel knows the track, but Mr. Market, as any good skier, will stay inside the track. Different paths on the same track. A matter of patterns, with a lot of variables.
A human can hardly conceive that this is even possible, while the neural networks crunch numbers. It’s a matter of data. Well collected and trained data.
By some extent, we can say that r.Virgeel can see into the future. Actually, he can show how market reacted under conditions similar to current ones. It’s not a superpower, it’s brute force. Something that a computer can do, not a human. So, r.Virgeel can show the bars into the future as the less improbable path that Mr. Market is going to run, inside the current track, under current conditions.