Sorry, I'm late to the "ML for MI" thread
RAMc writes on ML for MI
But I'm quite interested, so thought I'd take the liberty to post a few questions seperately in case they might not be seen tacked onto the old thread. Kudos to the OP!

For ML I've been putting in 60 to 100 financial and momentum features
Am curious about the features you used, do they include "fundamental ratios" e.g. P/B, P/S, etc often used in screens?

Screens seem similar to decision trees. Have you tried something like Briemans "Classification and Regression Trees" or random forests on fundamental data to create screens? This isn't "deep learning" a la neural networks, but it's a powerful ML algorithm.

Deep learning neural nets don't do well on numerical data. But I think they might handle categorizations such as "very low, low, medium, fairly high, high", which may be all the precision that's needed (see below).
Perhaps one could train a deep neural network on fundamental data and with the right prompts have them create a screen?
It could be cool and possibly useful to have "an AI" (I hate that terminology!) to suggest screens (Jim, your job is safe, I'm sure it'd never replace you!)

Below is a ChatGPT chat where I test how well it understands a categorization of data that has values e.g. converting values to "very low, low, medium, fairly high, high". It seemed to "get it", but you don't know when these things will start hallucinating:

Me:
If you had to pick the largest value from sets of values categorized as "very low, low, medium, fairly high, high", which one of these five categories would you pick?
ChatGPT:
To select the largest value among the categories "very low, low, medium, fairly high, high," the category "high" would be chosen.

Me:
How about a sort of middle value?
ChatGPT:
To select a middle value among the categories "very low, low, medium, fairly high, high," the category "medium" would be chosen.

Me:
What category would you assign to the ratio of values in "High" to values in "Low"?
ChatGPT:
The ratio of values in the "High" category to values in the "Low" category would likely be assigned to the "very high" category. This is because dividing a high value by a low value generally results in a significantly large ratio.