Awesome! Now that we're familiar with our dataset, we'll begin defining customer activity levels. First, we'll need to ensure our data is of good quality.
Our company sells three categories of products: food, clothing, and accessories. The
categories_6m columns denote how many categories of items a particular customer purchased from within the last 3 or 6 months, respectively.
For example, if a customer purchased only food (but not clothing or accessories) from our stores within the last 3 months, then
categories_3m would equal 1 for that particular customer. The maximum value for both these columns is 3, since our company only sells 3 categories of products.