Book “Machine Learning for Business Analytics”

‘Machine Learning for Business Analytics’ by Galit Shmueli, Peter C. Bruce, Kuber R. Deokar and Nitin R. Patel is a comprehensive and detailed book on the concepts, techniques and applications of machine learning in business analytics. This fourth edition, published in 2023, is aimed primarily at students and professionals seeking to master the tools and methods of predictive analysis and data mining.

The book is structured in nine parts, covering a wide range of topics from an introduction to the basic concepts of machine learning to advanced techniques such as deep learning and ensemble models. Each chapter is designed to stand alone, allowing readers to focus on the sections that interest them most.

Highlights

1. Accessibility : the book uses Analytic Solver Data Mining (ASDM) software for Excel, making machine learning concepts accessible even to those without programming skills.
2. Case studies: numerous real-life examples and case studies are included, helping to contextualise theoretical concepts and understand their practical application.
3. Update : this edition includes contemporary topics such as deep learning, ethics in data science and ensemble models, making it relevant to current market needs.
4. Pedagogy : the authors have extensive academic and professional experience, which is reflected in the clarity and depth of their explanations.

Weak points

1. ASDM dependency : although using ASDM facilitates learning, it may limit readers who prefer or use other machine learning tools.
2. Complexity : some chapters, particularly those on advanced techniques, may be difficult for complete beginners in machine learning to follow.

Avis

‘Machine Learning for Business Analytics is a must-read for anyone wishing to delve into the field of machine learning applied to business. The authors have succeeded in making complex concepts accessible through a clear pedagogical approach and the use of a practical tool such as ASDM. The updates included in this edition make it a relevant choice for students and professionals looking to stay at the cutting edge of current techniques.

However, it is important to note that the book can be dense and technical, requiring some grounding in statistics and data analysis to get the full benefit. In addition, the reliance on ASDM may be a hindrance to those using other machine learning platforms.