Introducing MLOps

Chapter 10. MLOps in Practice: Marketing Recommendation Engines

Makoto Miyazaki

Recommendation engines have become very popular in the last 20 years, from the first Amazon book recommendations to today’s generalized use in digital shops, advertisements, and music and video streaming. We have all become accustomed to them. However, throughout the years, the underlying technologies behind these recommendation engines have evolved.

This chapter covers a use case that illustrates the adaption of and need for MLOps strategies given the particularities of a fast-paced and rapidly changing machine learning model life cycle.

The Rise of Recommendation Engines

Historically, marketing recommendations were human-built. Based on qualitative and quantitative marketing studies, marketing moguls would set up rules that statically defined the impression (in the sense of advertising views) sent to a customer with given characteristics. This technique gave rise to the marketing data mining urban legend that a grocery chain discovered that men who bought diapers on Thursdays and Saturdays were more likely to buy beer as well and hence placing the two next to each other will increase beer sales.

Overall, recommendation engines created manually presented numerous bottlenecks that resulted in a significant amount of wasted money: it was hard to build rules based on many different customer features because the rule creation process was manual, it was hard to set up experiments to test many different ...