Extracting campaign finance data from gnarly PDFs using deep learning

Re:Extracting campaign finance data from gnarly PDFs using d... by lalaland1125 on Saturday June 22, 2019 @01:16PM (#20250629)

My personal bet is that you would have probably gotten better results by simply feeding your data into xgboost or lightgbm.

This current fad of focusing on neural networks just seems sorta silly when we have simpler and (often) better performing models. Just look at what sorts of models win kaggle competitions.

[ Parent | on HN ]

Re:Extracting campaign finance data from gnarly PDFs using d... by steve19 on Saturday June 22, 2019 @05:20PM (#20251779)

Maybe but I think 90% of the work is wrangling the data and understanding the problem, it wouldn't be that hard to substitute gradient boosting for the NN

[ Parent | on HN ]