Introduction to Algorithmic Marketing: Artificial Intelligence for Marketing Operations

The book is divided into six large and highly distinct chapters or parts, each of which deserves a dedicated review.The introductory chapter focuses on the relationship between marketing and mathematical optimization. It draws a big picture of marketing automation and its relationship with data science. I think that it connects business problems with technology in a very meaningful way and establishes a new fundamental framework that advances understanding of modern marketing.The second chapter focuses on machine learning and provides a decent overview of machine learning methods such as regression and clustering. While its aim is to “briefly review” the key methods, it is a bit overloaded with mathematical detail. Although the chapter is well structured, it can come across as overly complex for readers who are not familiar with ML and statistics, yet excessively shallow for readers who are.The third chapter is dedicated to targeted ads and promotions. This is where the book turns really valuable, as it delivers a very detailed and comprehensive description of methods for customer data analytics. Having read another great book on this subject, Winston’s Marketing Analytics: Data-Driven Techniques with Microsoft Excel, I have found this one to be more rigorous and advanced.The third and fourth chapters engage in a discussion about the implementation of search and recommendation services. While I see it as a good theoretical study, I think that it would benefit from more practical examples, using search engines like ElasticSearch or Solr.The last topic is price management. The chapter provides a number of techniques for retailers, but manufacturing and wholesaling are not covered. I especially appreciate that it describes practical models used by companies like RueLaLa and that it is not predominantly theoretical.Overall, I find this book to be well written, practically useful, and crisp. Despite covering many topics, it helps the reader master a solid methodology for applying ML and AI techniques in marketing.

This is probably the deepest and most comprehensive book on data-driven marketing. The scope is impressive; in addition to the introduction, the book has four massive chapters that cover promotions, searches, recommendations, and pricing. But what really stands out is the strong focus on the industrial reports and models used by leading companies such as LinkedIn and MediaMath.Keep in mind that it is a very technical book that assumes a good knowledge of statistics, and it is full of optimization models and numerical examples. This is good for developers and data scientists who want to understand the economic context and implementation details but not so good for business users, in my opinion.

I have many years of experience in ecommerce and data engineering, but this book really helped me to connect the dots between technology, data, and business. This is a solid reference that is likely to become a definitive book on the topic. Pros/cons:Pros:One methodology for all areas of marketing opsEnough details for implementationBest illustrations I have ever seen in a technical bookCons:Practical overall, but biased towards academics

Very rarely you come across a book that you just don't want to buy for yourself but also for your team. This book belongs in that category. Author has done justice to the marketing topics and able to compartmentalize marketing data science in right domains. I personally have 2 copies of the book and 3rd copy (paperback) on the way and that would be going out to the team.

A top-notch text that demonstrates true mastery in statistics and machine learning. Most of the knowledge here is portable to domains outside of the specific niche of "algorithmic marketing". If you're on the fence, just buy it. This will be a long-term facet in my ML library. Well done.

This book is great, which covers some detailed algorithm applyed to marketing.

best book on applied data science with Marketing

I couldn't understand the target audience of the book. It is neither a textbook nor a self-study book. The author simply compiled a list of mathematical models that can be applied in the marketing but didn't provide concrete examples with data to show how actually models are used. All you need is the table of content of the book and then you can read the Wikipedia pages for better understanding. I almost felt like the author rushed to get published and didn't actually want the reader to understand the concepts sufficiently and be comfortable enough to apply. The severe lack of example analysis using data sets corresponding to the compiled theories vividly manifests this shortcoming. in short, you can buy this book if you are interested to know which mathematical theories and tools people use in marketing without any expectation of being able to apply the theories.