How to create a non-contractual churn model for ecommerce

Knowing which of your customers are going to churn before it happens is a powerful tool in the battle against attrition, since you can take action and try to prevent...

How to classify customer service emails with Bart MNLI

Zero-shot learning, or ZSL, is a machine learning process commonly used for Natural Language Processing that allows you to generate predictions on unseen data without the need to train a...

How to calculate CLV using BG/NBD and Gamma-Gamma

Calculating Customer Lifetime Value or CLV is considered a really important thing in marketing and ecommerce, yet most companies can’t do it properly. This clever metric tells you the predicted...

How to auto-generate product summaries using deep learning

Several years ago, in one of my first Ecommerce Director roles, I worked with the ex-Myprotein founder to launch sports nutrition brand GoNutrition. As a “bootstrapped” startup, we were low...

How to assign RFM scores with quantile-based discretization

RFM segmentation is one of the oldest and most effective ways to segment customers. RFM models are based on three simple values - recency, frequency, and monetary value - which...

How to assess product copy using EQA models

In ecommerce, writing good product copy is both an art and a science. Not only does product copy need to be written in the correct tone and style for your...

How to analyse product consumption and repurchase rates

You can learn many things about your products from the purchase behaviours and product consumption and product replenishment of your customers. Some items are purchased individually, some items are purchased...

How to use Spintax to create content and ad copy in Python

If you’ve never heard of Spintax, you’ll definitely be aware of its typical usages. This text string replacement “language” is most commonly used for text spinning or article spinning, but...

How to use bagging, boosting, and stacking in ensembles

Ensemble models combine the predicitions of several different models to produce a single prediction, often with better results than can be achieved with a single model alone. There are several...