AI-Powered Marketing Analytics: Applied Methods for Managers
AI-Powered Marketing Analytics: Applied Methods for Managers
MarAI is an applied textbook for marketing analysts, data-literate managers, and advanced undergraduates who want to work through real marketing problems with quantitative methods, reproducible code, and carefully bounded AI support.
Current Status
UNDER PROOFREADING
Positioning
AI-Powered Marketing Analytics: Applied Methods for Managers is the applied marketing-analytics companion to Data-Driven Management: Statistics for Managers. DDMM establishes the statistical foundation. MarAI is where that foundation is put to work in customer analysis, campaign measurement, forecasting, competitive intelligence, and reporting for decision-makers.
Who It Is For
This title is being written for marketing analysts, data-literate managers, MBA and advanced undergraduate learners, and instructors who want a practical teaching line built around marketing use cases rather than generic statistics examples. It is especially suited to readers who already understand basic descriptive statistics, hypothesis testing, and simple regression, and now need a more applied path into marketing analytics.
Prerequisite Knowledge
The book assumes a working grasp of introductory statistics and a willingness to run examples in R. It does not require deep programming experience, and it does not assume that AI tools replace analytical judgment. The repo material is explicit that AI is used to accelerate specific steps such as code drafting, interpretation support, and stakeholder-ready summaries while the analyst retains responsibility for the method, checks, and conclusion.
Book Structure
The current book configuration already defines a five-part teaching sequence:
- Working with Marketing Data
- Understanding Customers
- Measuring Campaigns
- Competitive Intelligence
- Putting It Together
Across those five parts, the repo is already structured for twelve chapters covering customer segmentation, lifetime value, churn prediction, campaign ROI, attribution, demand forecasting, competitive positioning, and integrated reporting workflows.
What Already Exists In The Project
Book Build
The main Quarto book structure is already in place with the full chapter order, site configuration, bibliography, and shared templates.
Worked Examples
A parallel examples track is already planned as twelve worked units so that each method can be demonstrated on real marketing data.
Teaching Outputs
The repo already separates lecture decks and instructor materials into their own tracks, which makes the project suitable for later course adoption.
Shared Assets
Datasets, bibliographies, functions, and templates are organised in shared directories so the book, examples, and teaching materials can evolve from one asset base.
Current Build Status
The source project is already beyond the idea stage. Based on the repo status and current Quarto setup:
- the overall project structure is complete
- all twelve chapter stubs have been created
- chapter writing is in progress
- worked examples are in progress
- lecture decks, instructor pack, and quiz layers are planned next
That means this page represents a book line that is being actively assembled and proofread, not a placeholder concept with no production structure behind it.
Data And Workflow Approach
The repo is designed around publicly available datasets, open licences, and reproducible R workflows. The current material points to datasets such as Online Retail II, Bank Marketing, and the UK Retail Sales Index, with chapter-level codebooks and provenance notes held in the shared dataset folders. This is important for instructors and self-directed readers who need examples that can actually be rerun and inspected.
What To Expect At Release
When the proofreading and content pass are complete, this title is intended to ship as more than a book file. The source structure already anticipates a teaching package with the book, worked examples, slide decks, instructor resources, and reusable datasets aligned to the same chapter sequence.