Mckinsey Interview Questions | Practical Problem
Question
If you are having 4GB RAM in your machine and you want to train your model on a 10GB data set. How would you go about this problem?
in progress
1
Machine Learning
4 years
2 Answers
1007 views
Great Grand Master 0
Answers ( 2 )
We can use spark or hadoop.
Batch processing can accomplish this.
There might also be situations when a lot of data points add little or no value to the model. In such cases, we can sample a smaller proportion of the data to run the model on, without compromising on performance