# Pros and cons of using the zscore of a dataset before normalizing it during feature engineering?

Normalization is a common feature engineering technique. However, this post used standardize(zscore) on the dataset before normalizing it.

I think that would result in losing some of the information in data.

What are the pros and cons of doing this?

Normalizing an already normalized dataset should not change anything unless for some reason a different normalization scheme is used.

Z-scores normalisation are a way to compare results from a test to a “normal” population and bring them to a same comparable scale. Advantages of ZScore can thus be:

$$z\_score = \frac{x-\bar x}{\sigma}$$

The Z score normalisation has the following advantages:

1. Z Score can be used to compare raw scores that are taken from different tests
2. Z score takes into account both the mean value and the variability in a set of raw scores.

And the Disadvantages of Z score are:

1. Z Score always assume a normal distribution.
2. If the data is skewed, the distribution of the left and right of the origin line is not equal.