Preface

This book grew out of a practical need: students and practitioners in African organisations had access to good conceptual introductions to business analytics but lacked a tutorial-style resource that walked them, step by step, through implementation — from raw data to actionable insight — using real-world tools and locally relevant examples.

The analytical landscape it surveys was partly inspired, at the outset, by the broad framework laid out in Key Business Analytics by Bernard Marr, a useful map of the techniques that organisations use. What you hold now, however, is an entirely independent work. Every technique is explained from first principles. No prior knowledge of the original map is assumed or needed.

What This Book Is

This is a tutorial textbook. It is not a reference manual and not a theoretical treatise. It is a guided learning journey, structured so that a motivated reader with only a secondary-school understanding of mathematics and statistics can, by working through the chapters in sequence, arrive at genuine competence in applying AI and machine learning to business data.

Each chapter:

Explains the theory in intuitive language, with key formulae presented clearly
Implements the technique in both R and Python, with runnable code you can adapt immediately
Grounds the analysis in a Nigerian or African business case wherever possible
Tests your understanding with section-level review questions and end-of-chapter exercises

Full mathematical derivations — for readers who want to understand why the formulae work — appear in each chapter’s appendix, clearly separated from the main text.

Who This Book Is For

Undergraduate and MBA students taking analytics, data science, or quantitative methods courses
Practitioners in finance, marketing, operations, HR, and strategy who want to work with data themselves
Analysts who know one language (R or Python) and want to become fluent in both
Anyone curious about how AI and machine learning actually work, explained without mystification

The only prerequisites are basic arithmetic, some familiarity with spreadsheets, and a willingness to run code and make mistakes.

How the Book Is Structured

The book is divided into seventeen parts. The first six parts build foundational skills — data literacy, statistics, visualisation, hypothesis testing, regression, and classification. Parts VII through X introduce the specialised method families — time series, text analytics, networks, and recommendation systems. Part XI covers deep learning at an accessible level. Parts XII through XVI apply all these methods to the major business domains: finance, customer management, marketing, operations, and people analytics. Part XVII covers simulation and uncertainty.

The parts are designed to be read in order the first time through. Once you have completed the foundations, individual later chapters can be revisited independently.

The Computing Environment

All code runs in RStudio or Positron, and uses both R and Python in parallel. Code appears in tabbed panels: click the “R” tab or the “Python” tab to see each implementation. Chapter 1 guides you through the complete setup.

A Note on Datasets

Nigerian and African data are used wherever available and appropriate. Sources include the Nigerian National Bureau of Statistics (NBS), the Central Bank of Nigeria (CBN), the National Information Technology Development Agency (NITDA), the Nigeria Inter-Bank Settlement System (NIBSS), the Economic Community of West African States (ECOWAS), the African Development Bank (AfDB), and the World Bank’s Africa portal. Where no suitable local dataset exists, internationally available data with African applicability is used.

All datasets are either publicly available or synthetic but realistic. Download scripts for every dataset used in the book are provided in Appendix B.

Bongo Adi April 2026

--- title: "Preface" number-sections: false --- # Preface {.unnumbered} This book grew out of a practical need: students and practitioners in African organisations had access to good conceptual introductions to business analytics but lacked a tutorial-style resource that walked them, step by step, through implementation — from raw data to actionable insight — using real-world tools and locally relevant examples. The analytical landscape it surveys was partly inspired, at the outset, by the broad framework laid out in *Key Business Analytics* by Bernard Marr, a useful map of the techniques that organisations use. What you hold now, however, is an entirely independent work. Every technique is explained from first principles. No prior knowledge of the original map is assumed or needed. ## What This Book Is This is a **tutorial textbook**. It is not a reference manual and not a theoretical treatise. It is a guided learning journey, structured so that a motivated reader with only a secondary-school understanding of mathematics and statistics can, by working through the chapters in sequence, arrive at genuine competence in applying AI and machine learning to business data. Each chapter: - **Explains the theory** in intuitive language, with key formulae presented clearly - **Implements the technique** in both R and Python, with runnable code you can adapt immediately - **Grounds the analysis** in a Nigerian or African business case wherever possible - **Tests your understanding** with section-level review questions and end-of-chapter exercises Full mathematical derivations — for readers who want to understand *why* the formulae work — appear in each chapter's appendix, clearly separated from the main text. ## Who This Book Is For - **Undergraduate and MBA students** taking analytics, data science, or quantitative methods courses - **Practitioners** in finance, marketing, operations, HR, and strategy who want to work with data themselves - **Analysts** who know one language (R or Python) and want to become fluent in both - **Anyone** curious about how AI and machine learning actually work, explained without mystification The only prerequisites are basic arithmetic, some familiarity with spreadsheets, and a willingness to run code and make mistakes. ## How the Book Is Structured The book is divided into seventeen parts. The first six parts build foundational skills — data literacy, statistics, visualisation, hypothesis testing, regression, and classification. Parts VII through X introduce the specialised method families — time series, text analytics, networks, and recommendation systems. Part XI covers deep learning at an accessible level. Parts XII through XVI apply all these methods to the major business domains: finance, customer management, marketing, operations, and people analytics. Part XVII covers simulation and uncertainty. The parts are designed to be read in order the first time through. Once you have completed the foundations, individual later chapters can be revisited independently. ## The Computing Environment All code runs in **RStudio** or **Positron**, and uses both **R** and **Python** in parallel. Code appears in tabbed panels: click the "R" tab or the "Python" tab to see each implementation. Chapter 1 guides you through the complete setup. ## A Note on Datasets Nigerian and African data are used wherever available and appropriate. Sources include the Nigerian National Bureau of Statistics (NBS), the Central Bank of Nigeria (CBN), the National Information Technology Development Agency (NITDA), the Nigeria Inter-Bank Settlement System (NIBSS), the Economic Community of West African States (ECOWAS), the African Development Bank (AfDB), and the World Bank's Africa portal. Where no suitable local dataset exists, internationally available data with African applicability is used. All datasets are either publicly available or synthetic but realistic. Download scripts for every dataset used in the book are provided in Appendix B. --- *Bongo Adi* *April 2026*