Hi!
Look please more careful on how I prepare data — it’s not a 2D array aka normal image that we pass to CNN (and it supposed to work well), it’s 1D array with multiple channels aka variables aka dimensions (open, high, low, close, volume), where on every time step we have a vector of ohlcv values.

We can work with this kind of sequences both with CNNs/RNNs, but latter ones need different preparation of input data (it’s not the best solution to pass returns there, raw values are a bit better) and hyperparameters (for example initialization of forget gate). That’s why I used CNNs, because for teaching or demonstration purpose they are better.

Co-founder of consulting firm Neurons Lab and advisor to AI products builders. On Medium, I write about proven strategies for achieving ML technology leadership

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store