
Deep learning vs tabular models (Ep. 217)
Data Science at Home
00:00
How to Predict a Target Function Using Random Forest
Before throwing yourself into the deep learning world, look at your data first. Try to understand if your data is affected or the target function is affected by strong irregular patterns and that would give you already a very interesting suggestion of what is the method that is most appropriate for that particular data set. The best model is essentially very much bound to the particular data and to the irregularities and the geometry that that data represents.
Transcript
Play full episode