Feature scaling is an important part of data pre-processing.
Often, numeric variables in a dataset have very different scales. For example, let's say we have a dataset which includes the area of a house (in square feet) and its corresponding price (in US dollars). Typically, the area of the house will be in the range 500 - 5000 square feet, but the price will range from $100,000 - $5,000,000. As you can see, the scale of the features are very different. In this case, the price is almost 1000x square feet area.
In this tutorial, we will first talk about how having all the variables be in a similar scale helps us. Then, we will talk about various methods to perform scaling.