334
submitted 1 day ago* (last edited 1 day ago) by cypherpunks@lemmy.ml to c/programmerhumor@lemmy.ml
you are viewing a single comment's thread
view the rest of the comments
[-] idriss@lemmy.ml 6 points 19 hours ago

A similar experiment I did comes to mind from 3 years ago.

For the fun of it I was trying to train a few deep neural network configurations (LSTM, a few variations of FCNs, ...) to trade shitcoins and downloaded 4 years of 1h candles.

The first easiest idea was to prepare the training data to fire three signals, buy, sell, do nothing (I know a terrible choice). The cost function was setup to do the simple thing and maximize the overall profit (I know an other terrible choice). Fast forward 30min of training and the final outcome is a model that outputs "do nothing" in 100% of the cases.

[-] MonkeMischief@lemmy.today 6 points 18 hours ago

Fast forward 30min of training and the final outcome is a model that outputs "do nothing" in 100% of the cases.

To be fair, your program demonstrated the most reliable way to win at crypto! ๐Ÿ˜‰

this post was submitted on 22 Feb 2026
334 points (98.8% liked)

Programmer Humor

41092 readers
120 users here now

Post funny things about programming here! (Or just rant about your favourite programming language.)

Rules:

founded 6 years ago
MODERATORS