ASOS Uses Machine Learning To Understand Customer Value (For the technically inclined, a full description is in the paper below)
The paper discusses a machine-learning framework that uses embedding in looking across all of product's customer views, and then assigns a value to each customer based on the characteristics of customers who he or she appears close to in product's view sequences. This gives a data output that can help differentiate high value from low value customers. This method results in an uplift in AUC (Area Under Curve), meaning that the system with the learned features was better than the system without learned features at distinguishing between the two classes (high-value and low-value). This demonstrates how new kinds of machine learning can help understand how analysis of digital behavior can inform better marketing activities and be employed by retailers and marketers to solve a number of potential challenges.