This article aims to help data scientists and machine learning developers save precious time when faced with the challenges of preprocessing text data. It is based on a case study from the field of e-commerce and a presentation delivered during an ML meetup hosted by ShopGun and Nordic.ai on the 15th of February 2018 in Copenhagen. To make it easier to digest I've boiled it down to 5 helpful tips which I wish I'd known when I begun working on this project (each marked with a #). We will be using a tiny sample of our data and taking it through every recommended preprocessing step to really get a feel for what's going on. The way we preprocess data should usually be tailored to the problem that we're trying to solve.