There is nothing in the community guidelines about having to stay on topic and to only talk about what's on the article.
There is however:
Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith.
Please don't comment on whether someone read an article. "Did you even read the article? It mentions that" can be shortened to "The article mentions that".
I think the pattern In these posts is that they are looking for models that are explainable and have the potential for low latency, like the kann fpga project. While more general and opaque classifiers possibly work they are unlikely to work at the speed and risk constraint required to make money.
I apologise if I completely missed the point, it is not my field at all.
(Yes I read the article)
"But what kind of data is market data? ... is it continuous or discrete? Market data seems to have features of both. An order book evolves via a series of turns as market participants put on, or take away, resting orders; there is no doubt a discrete action space. And yet, many of the most important parameters of a given order, like its price, have such a high cardinality that they basically appear continuous. ...
One way to explore these complications is to treat your data as if it’s continuous and see how that breaks down. "
"Most of the project was spent grappling with a fundamental problem: market data is neither fully continuous nor fully discrete."
I think it is continuous because it is an emergent property of the market system. There is a video where the guy tried to see if market structure was "real" by modeling it. He had trouble in the beginning but when he added an order book the structures and patterns (Head and Shoulder, Bull Flags, Double Tops) appeared. It's called:
"I made a Market Simulation to see if Patterns are Real" by Krafer
Yes, you are right. I agree with that. The additional thing is that the orderbook can be looked at like (similar, not exact) molecules of water. A single molecule of water is not wet. And a single molecule of water can't be modeled by fluid dynamics. You can think of the orders in the orderbook as molecules of water. When there is enough of those discrete orders and transactions then what "emerges" is something greater that the individual parts. At a certain volume or mass the molecules of water form drops of water and those form masses of water that can be modeled with fluid dynamics and treated continuously.
You do say this as well:
"A model can approximate it in a continuous way, sure, but an actual orderbook will always be discrete."
Which is the same as saying (I might be wrong though, and I am not "quoting" to indicate you said it):
"An actual orderbook is discrete AND can be modeled in a continuous way."
I think that means we agree and arrive at the same place even if I think it's due to emergence in the market system and you think it is just something that exists in that market system.