Is there any data scaling methods except for Min-Max Normalization and Quantile transformation that keeps the range between [0,1]?

Question

I have been working on a machine learning project and I have been trying to scale the features before feeding it to my model. I know Min-Max Normalization and Quantile Transformation scales down the features in the range of 0 and 1. I was wondering if there’s any other scaling method or way through which the range can be scaled down between 0 and 1.

Answer 1

• You scale the features based on their measure of central tendency and variability.
• Eg. If there are outliers You can use RobustScaler(), to remove the outliers and then use either StandardScaler or MinMaxScaler for preprocessing the data
• For scaling down the features into particular range, you have Normalization techniques, other than that you have to write your method to scale the features into particular range without loosing the information.
• look into this notebook for feature scaling techniques https://www.kaggle.com/code/aimack/complete-guide-to-feature-scaling .