Why we use -1 to impute for missing values?



How replacing missing value with -1 will help us? What is the concept behind imputing -1 and why with -1 ? What happens if the columns with missing value contains -1 already?


@Raghuvaran_Raghu -1 is just a constant, you could obviously replace it with any constant you want, although I strongly recommend -1 since tree based models are known to identify them as missing values.


Replacing with -1 is not the best idea…but mostly certainly better than replacing it with +1.

Best is you perform imputation that gives realistic values and additionally add a column indicating missing values.