Read on Twitter
They say:
"Kaggle doesn't teach you how to translate a business problem into machine learning terms"
This is NOT true
You CAN learn a great deal from @kaggle
Let me tell you how you can do it in 4 simple steps. None of them requires taking part in a competition
Thread
"Kaggle doesn't teach you how to translate a business problem into machine learning terms"
This is NOT true
You CAN learn a great deal from @kaggle
Let me tell you how you can do it in 4 simple steps. None of them requires taking part in a competition
Thread
Explore 
Look at the past competitions Find 20 competitions that are interesting Put them in a spreadsheet
Understand each competition Read the problem definition Check the data the organizers prepared Check the metric they used The organizers did a lot of hard work! Learn from it
Analyze the data Download the dataset Find EDA kernels, reproduce them Find "getting started" kernels, reproduce them
Check the solutions Find the solution-sharing threads Read the solutions Focus on the high-level description of features and tricks Note what worked and what didn't Ignore leaks, magic features, and ensembles
Do that for 20 competitions and you'll become a pro!
