What I've been working on recently, and a request for code review
I've been working on a plugin for Stata which implements [Empirical Dynamic Modelling](https://www.researchgate.net/publication/317339714_Empirical_dynamic_modeling_for_beginners), a stats tool with the funnily misleading acronym EDM. Have you ever heard the line "correlation does not equal causation"? Well EDM aims to fix that.
The biggest difficulty, in my opinion, with machine learning problems is after you've got a working solution. You're staring at some accuracy figure, say 95%, and wondering 'how high can this go?' There are a huge number of options for that next step.