this thread and viz might be interesting for you:
source:
Compared to classic ML models DNNs possess less structure and can learn more complex and abstract relationships given sufficient amount of data. However if you have domain knowledge that you can model in a handful of features, classic ML can be very powerful, too. Especially if you have rather a limited amount of data (which typically can be represented in structured tables), see also this thread: Why traditional Machine Learning algorithms fail to produce accurate predictions compared to Deep Learning algorithms? - #2 by Christian_Simonis
That beeing said:
In this case a simple NN (without advanced layers like conv / pooling) just as it is used since decades rather fits classic ML as Tom pointed out in this previous post.
Hope that helps!
Best regards
Christian