← Research logMachine Learning
KILLED · pareidolia
#

A convolutional net trained on rendered candlestick chart images learns profitable visual patterns end-to-end.

$$ \hat y = \text{softmax}\big(W\cdot \text{CNN}(\text{image}(P_{t-k:t})) + b\big) $$

Render OHLC windows to images, train a CNN classifier on forward-return labels, strict temporal split.

Validation accuracy~51%
Learned featuresmostly recent-trend slope
vs a 2-feature logistic baselineno improvement
KILLED
Rendering numbers as pixels and convolving them throws away precision and adds no information. The CNN rediscovers "recent slope" — reproducible with a two-line baseline — at far higher cost. Pareidolia with a GPU. Killed.
Turning structured numeric data into images to use a CNN is almost always a step backwards. The net can only learn what the pixels preserve, and pixels lose precision.

We publish the failures too.

This is one of 100+ documented hypotheses. Browse the full lab notebook, or see the strategies that survived into production.