Guys, I understand, that many of you already know this, but want to remind that kaggle has competition 'Predict CO2 Emissions in Rwanda" which use very similar data and you can get some ideas from notebooks for this competition.
Hello @yanteixeira, I know I'm not the one who asked the question, but my CV scores and LB scores are not really far from each other (around 14 using 20 folds). I also wonder how you dealt with the high dimensionality of the data and multicollinearity. Do you have any Kaggle references? Thanks in advance.
Thank you. Can I ask you if there is a question?
Thank you! High dimensionality is my problem, how many features did you use?
@serg132003 do your CV scores match your LB scores?
Hello @yanteixeira, I know I'm not the one who asked the question, but my CV scores and LB scores are not really far from each other (around 14 using 20 folds). I also wonder how you dealt with the high dimensionality of the data and multicollinearity. Do you have any Kaggle references? Thanks in advance.
Hi @erg132003 Are we allowed to use any modeling technique apart from the one stated in the starter notebook?
Thank you for the insights