“Showing up is 80 percent of life.” — Woody Allen, via Marshall Brickman
“Machine learning can feel intimidating at first — the most important skills are not writing complex code, but knowing which questions to ask, which tools to reach for, and how to evaluate whether an AI system is doing what you actually need it to do.”
| Course Code | BUS 580 — Special Topics in Business Analytics |
| Course Title | Marketing Analytics & Machine Learning for Business |
| Credit Hours | 3 Units |
| Level | Graduate (MBA / MS) |
| Format | Fully Online (Asynchronous with optional synchronous check-ins) |
| Duration | 8 Weeks — June 2026 to August 2026 |
| Meeting Pattern | Flexible weekly modules; live Q&A sessions (schedule TBA) |
| Course Portal | Canvas / University LMS |
| Name | [Instructor Name] |
| [instructor@csuci.edu] | |
| Office Hours | By appointment — please email to schedule a Zoom session |
| Response Time | Within 2 business days for Canvas messages and email |
This graduate course integrates two complementary disciplines — marketing analytics and machine learning / artificial intelligence — into a single, cohesive learning experience. Students develop the technical fluency and strategic judgment needed to lead data-driven initiatives in modern organisations.
Drawing on the instructor’s MKTG 4000 (Marketing Analytics) and BUS 6600 (Machine Learning & AI for Business) courses, this course treats marketing research and machine learning not as separate fields but as an end-to-end analytical pipeline: from problem formulation and survey design through to predictive modelling, segmentation, and AI-powered decision-making.
Across 8 weeks, students work with R and accessible cloud tools to analyse real data, build models, and communicate findings to business stakeholders. No prior programming experience is assumed; skills are built progressively each week.
This course is designed for graduate students who aspire to become analytically fluent leaders — professionals who can direct data science teams, commission research, interpret model outputs critically, and communicate evidence-based strategy.
Upon successful completion of this course, students will be able to:
| Learning Outcome | |
|---|---|
| LO1 | Describe the role of marketing research and data analytics in strategy development, and connect them to broader machine learning and AI capabilities. |
| LO2 | Design and evaluate marketing research studies, including survey instruments, sampling strategies, and experimental designs. |
| LO3 | Apply supervised learning methods — regression, classification, and forecasting — to real-world marketing and business datasets using R. |
| LO4 | Apply unsupervised learning techniques — clustering, segmentation, and association rules — to identify patterns and opportunities in customer data. |
| LO5 | Evaluate model performance using appropriate metrics and translate quantitative findings into actionable business recommendations. |
| LO6 | Critically assess the ethical, legal, and societal implications of AI and algorithmic decision-making, including bias, fairness, and regulatory context. |
| LO7 | Design a complete AI/analytics project proposal: problem scoping, data plan, model selection, success criteria, and risk assessment. |
| LO8 | Communicate analytical insights clearly to both technical and non-technical audiences through written reports, visualisations, and presentations. |
| Role | Reference |
|---|---|
| Primary | Miller, T. W. (2015). Marketing Data Science: Modeling Techniques in Predictive Analytics with R and Python. Pearson FT Press. [Available via CSUCI Library — no purchase required] |
| Supplementary | James, G., Witten, D., Hastie, T., & Tibshirani, R. (2023). An Introduction to Statistical Learning with Applications in R (2nd ed.). Springer. [Free PDF: statlearning.com] |
| Supplementary | Lantz, B. (2023). Machine Learning with R (4th ed.). Packt Publishing. |
| Business Context | Agrawal, A., Gans, J., & Goldfarb, A. (2018). Prediction Machines: The Simple Economics of Artificial Intelligence. Harvard Business Review Press. |
Zero-cost commitment: All required readings are accessible at no cost through the CSUCI Library, free PDFs, or open-licensed repositories. You will not need to purchase any textbook.
All software used in this course is free:
tidyverse,
ggplot2, caret, rpart,
randomForest, arules, factoextra,
tidytextInstructor R resources and notebooks: rpubs.com/utjimmyx
This course is fully blended — marketing research methodology and machine learning are taught together each week, not in sequence. Each module pairs a foundational analytics concept with a complementary ML technique applied to marketing and business data.
The 8-week arc moves from foundations and research design → supervised learning → unsupervised learning and segmentation → AI applications and ethics → capstone project.
| Week | Dates | Module Title | Topics Covered | Deliverables Due |
|---|---|---|---|---|
| Week 1 | Jun 1–7 | Foundations: Marketing Research & the Analytics Pipeline | What is marketing analytics? What is ML/AI? The end-to-end analytics lifecycle; problem formulation; data types; intro to R and ggplot2; Miller Ch. 1–2; Prediction Machines Ch. 1 | Syllabus agreement; discussion post 1 |
| Week 2 | Jun 8–14 | Research Design, Survey Methods & Data Collection | Primary vs. secondary data; survey design and pitfalls; Qualtrics/Google Forms; sampling methods; sample size; exploratory analysis; Miller Ch. 3; Smith & Albaum (2010) | Lab 1 — R basics; Discussion 2; DataCamp certificate 1 (Intro to R) |
| Week 3 | Jun 15–21 | Supervised Learning I — Regression & Forecasting | Simple and multiple linear regression; interpreting coefficients; RMSE, R²; forecasting and time series concepts; hands-on: predicting sales with lm() in R; Miller Ch. 5; ISLR Ch. 3 | Lab 2 — Regression in R; Discussion 3; Project proposal due |
| Week 4 | Jun 22–28 | Supervised Learning II — Classification & Prediction | Logistic regression; decision trees; confusion matrix; accuracy, precision, recall, ROC-AUC; customer churn; credit risk; Miller Ch. 6–7; ISLR Ch. 4, 8 | Lab 3 — Classification in R; Assignment 1 due; Discussion 4 |
| Week 5 | Jun 29–Jul 5 | Unsupervised Learning — Segmentation & Association Rules | K-means clustering; hierarchical clustering; customer segmentation; association rule mining (Apriori); market basket analysis; Miller Ch. 8–9; ISLR Ch. 12 | Lab 4 — Segmentation & association rules; Discussion 5; DataCamp certificate 2 (Marketing Analytics in R) |
| Week 6 | Jul 6–12 | AI Applications in Marketing (NLP, Recommenders, LLMs) | Sentiment analysis and text mining; NLP for marketing (reviews, social listening); recommendation systems; overview of LLMs and ChatGPT in business; Miller Ch. 10–11; Lantz Ch. 10 | Lab 5 — Sentiment analysis; Discussion 6; Midterm take-home project due |
| Week 7 | Jul 13–19 | AI Ethics, Strategy & Governance | Algorithmic bias and fairness; explainability; EU AI Act, GDPR, California AI legislation; AI strategy — build vs. buy vs. partner; communicating AI to leadership; O’Neil (2016) Ch. 1–3 | Lab 6 — Ethics case analysis; Discussion 7; Assignment 2 due |
| Week 8 | Jul 20–Aug 2 | Capstone: Project Presentations & Course Reflections | Group project presentations; peer evaluation; individual self-reflection; portfolio review; course wrap-up | Group project report + code due; Presentation (live or recorded); Peer evaluation; Self-reflection essay |
Subject to change. The schedule may be adjusted as the course progresses. All updates will be communicated via Canvas with reasonable advance notice.
| Assessment Task | Weight | Mode |
|---|---|---|
| Participation & Engagement | 10% | Individual |
| Weekly Labs (6 labs × ~1.5% each) | 9% | Individual |
| DataCamp Certificates (2) | 6% | Individual |
| Group Discussions (7 × ~1% each) | 7% | Group/Individual |
| Assignment 1 — Supervised Learning Report | 8% | Individual |
| Assignment 2 — Unsupervised Learning Report | 8% | Individual |
| Midterm — Take-Home Data Project | 12% | Individual |
| Group Project Report | 22% | Group (3–4) |
| Group Project Presentation + Peer Eval | 13% | Group (3–4) |
| Individual Self-Reflection Essay | 5% | Individual |
| Total | 100% |
Six hands-on R labs submitted via Canvas, one for each of Weeks 1–7 (Week 8 is presentation week). Labs are completed individually. Initial drafts are due by the second session of each week; final polished submissions are due by end of the week. Labs are published to RPubs and the link submitted to Canvas.
Each lab pairs a marketing problem with an R technique drawn from that week’s module. There is no penalty for incomplete initial drafts — the goal is to attempt the analysis before the final submission.
Students complete two DataCamp certificates at no cost via instructor-provided access (available from Week 1):
Seven asynchronous weekly discussion threads on Canvas. Each discussion is tied to a real-world case, reading, or analytical result from that week. Students post an initial response and reply substantively to at least two peers. Discussion prompts are released at the start of each week.
Using a provided marketing dataset, students conduct an end-to-end supervised learning analysis in R covering: (1) exploratory data analysis with visualisations, (2) a regression model, (3) a classification model, and (4) a plain-English business interpretation written for a non-technical manager.
Submitted as: an R Markdown report (knitted to HTML or PDF) + 600-word executive summary.
Due: End of Week 4.
Marking criteria: Data exploration and visualisation (25%) | Model implementation (30%) | Model evaluation and interpretation (25%) | Business communication (20%)
Students apply clustering and/or association rule mining to a dataset of their choice (instructor-approved). The report frames the analysis as a marketing business problem, presents results visually, and provides two or more actionable recommendations.
Submitted as: an R Markdown report (knitted to HTML or PDF) + 600-word management summary.
Due: End of Week 7.
Marking criteria: Problem framing (20%) | Technical implementation (30%) | Results and visualisation (25%) | Recommendations (25%)
Rather than a traditional exam, the midterm is an individual, take-home data project using a real dataset (sourced from Kaggle or a marketing database). Released at the end of Week 5; due end of Week 6.
The dataset is drawn from one of the following domains (confirmed by Week 4):
Required deliverables:
Required analysis steps:
| Criterion | Weight |
|---|---|
| Data exploration and cleaning | 20% |
| Supervised model implementation and evaluation | 25% |
| Unsupervised model implementation and interpretation | 25% |
| Business recommendation quality and clarity | 20% |
| Report presentation and reproducibility | 10% |
This is an individual assessment. Students may consult course materials, textbooks, and R documentation but must complete all analysis and writing independently. All AI tool use must be disclosed per the course AI policy.
The group project is the centrepiece of the course. Working in groups of 3–4, students identify a real marketing or business problem and develop a complete analytics solution that integrates both marketing research methods and machine learning.
The project must include: problem scoping, data sourcing and preparation, model development in R (both supervised and unsupervised components), results evaluation, ethical review, and a practical implementation roadmap informed by Miller (2015).
Groups must notify the instructor of their proposed topic and dataset by end of Week 3.
Deliverables:
| Component | Weight | Due |
|---|---|---|
| Group Project Report (2,500–3,500 words + R Markdown code) | 22% | Examination period |
| Group Project Presentation (12-min + 3-min Q&A) | 10% | Week 8 |
| Peer Evaluation (individual, submitted separately) | 3% (within group project) | Week 8 |
Marking criteria: Problem framing and scoping (15%) | Data preparation and modelling (30%) | Evaluation and interpretation (20%) | Ethical and strategic analysis (15%) | Presentation quality (20%)
Peer evaluation: At the end of the semester, each student completes a peer evaluation rating their teammates’ contributions. The team member with the highest peer evaluation score receives 100% of the project grade; others receive a proportional share. For example, if a student’s score is 80% of the top score and the project earns 90%, that student’s project grade is 80% × 90% = 72%.
A 400–600 word essay submitted during Week 8. Students reflect on: (1) their learning journey across the 8 weeks, (2) how their view of marketing analytics or AI has changed, and (3) how they plan to apply these skills in their career. An optional social media / RPubs portfolio reflection may be included.
| Grade | Score Range | Description |
|---|---|---|
| A | 93–100% | Outstanding — mastery of concepts and applied skills |
| A- | 90–92.99% | Excellent — strong performance with minor gaps |
| B+ | 87–89.99% | Very good — solid understanding throughout |
| B | 83–86.99% | Good — competent grasp of core material |
| B- | 80–82.99% | Satisfactory — meets most learning outcomes |
| C+ | 77–79.99% | Adequate — meets learning outcomes with some gaps |
| C | 70–76.99% | Passing — minimum standard met |
| D | 60–69.99% | Marginal pass — significant gaps in understanding |
| F | Below 60% | Fail — does not meet minimum requirements |
This is a fully online course. Active participation in weekly discussions, lab submissions, and synchronous check-ins (where offered) constitutes attendance. Students who fall more than one week behind without communication may be referred for academic support.
Engagement includes: completing readings before discussions open; submitting labs on time; contributing substantively to group work; and participating in peer evaluation. Participation (10%) reflects the quality and consistency of these contributions across the semester.
All graded work submitted late without prior approval is penalised at 10% per calendar day from the due date/time. Extension requests must be submitted via Canvas message at least 48 hours before the deadline with a brief explanation. Medical or other extenuating circumstances must be documented through the university’s official process.
Re-grade requests must be submitted in writing within three business days of the grade being returned. Please include the graded work and a brief letter explaining the basis for the request.
All submitted work must be the student’s own, completed in accordance with the CSUCI Student Conduct Code. Plagiarism, contract cheating, and unauthorised reproduction of others’ work will result in a zero for the assessment and may result in further disciplinary action.
This course teaches about AI — students are expected to engage with AI tools thoughtfully, not avoid them or misuse them.
Suggested disclosure template:
“I acknowledge the use of [tool name] in completing this assignment. I used it to [describe purpose — e.g., debug an R error / understand a concept / brainstorm structure]. All analysis, interpretation, and written conclusions are my own.”
Submitting AI-generated text as your own analysis without disclosure is academic dishonesty.
Students requiring accommodations due to a documented disability or other circumstances should contact the instructor within the first two weeks of the course. CSUCI is committed to an inclusive learning environment. Please also visit the university’s Disability Resource Programs office for formal accommodation support.
The instructor will respond to Canvas messages and email within two business days. For complex questions about assignments or course content, a Zoom office hours appointment is strongly preferred over email. All course announcements, assignment briefs, and lab templates are posted to Canvas.
The number one concern of graduate business students is whether they will leave their programme with marketable, practical skills. This course is designed to address that concern directly. Marketing analytics and AI literacy are among the most in-demand capabilities across industries — and fewer than 5% of business programmes teach them using real programming tools like R.
You do not need prior coding experience. R skills are built step by step across the 8 weeks, and every technique is introduced through a concrete business problem drawn from Miller (2015). By the end of this course you will have a portfolio of published R analyses on RPubs that you can share with employers.
Come curious. Ask questions. Make mistakes in the labs. That is how this works.
Free Online Learning:
Instructor R Resources:
Industry Reading:
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2023). An Introduction to Statistical Learning (2nd ed.). Springer.
Lantz, B. (2023). Machine Learning with R (4th ed.). Packt.
Miller, T. W. (2015). Marketing Data Science: Modeling Techniques in Predictive Analytics with R and Python. Pearson FT Press.
Agrawal, A., Gans, J., & Goldfarb, A. (2018). Prediction Machines. HBR Press.
O’Neil, C. (2016). Weapons of Math Destruction. Crown Publishing.
Smith, S. M., & Albaum, G. S. (2010). An Introduction to Marketing Research. Qualtrics Labs. Available: semanticscholar.org
Zumel, N., & Mount, J. (2020). Practical Data Science with R (2nd ed.). Manning.
This syllabus is subject to change. Any modifications will be
communicated via Canvas with reasonable notice.
Last updated: May 2026
Produced using R 4.5.3 and R Markdown.