DATA5000 · KAPLAN BUSINESS SCHOOL · T1 2026
Artificial Intelligence
Programming in
Business Analytics
Designing, programming, and applying AI models to real-world data — from predictive analytics and causal ML to generative AI, prompt engineering, and agentic frameworks.
12 Weeks covering AI fundamentals through agentic frameworks and ethics
3 Assessments: individual project, team presentation, and analytics capstone
100% Python-based — open-source tools on Google Colab, no local install required
Pre-requisite: None · Co-requisite: DATA4800 · Credit Points: 4 · Mode: On-campus & Online
Your Instructor 02 / 07
SV
Stephen Vu
Instructor — DATA5000: Artificial Intelligence Programming in Business Analytics

Education

PhD in Recommender Systems Queensland University of Technology (QUT)

Current Position

Postdoctoral Researcher QUT × Department of Agriculture, Water and the Environment
Data Science & Artificial Intelligence

Teaching Experience

4 years of university teaching QUT · Kaplan Business School · Central Queensland University · James Cook University

Subject Overview 03 / 07

AI is not just a tool —
it's a business capability

This subject teaches you to design, program, and apply AI models to real-world business data. You will source, store, and prepare data to build AI applications that uncover insights of strategic value — working with financial, social media, text, image, and speech data.

From predictive modelling and causal inference through to generative AI and agentic frameworks, you will build a full spectrum of AI capabilities grounded in Python and applied business contexts.

  • LO1 Ethically source, store, prepare, and analyse data for AI applications
  • LO2 Create an AI application within a business context using Python
  • LO3 Utilise AI to analyse and evaluate business decisions and processes
  • LO4 Create advanced business insights through ethical AI application
12-Week Journey
W1
Intro to AI & Data Management
W2
Predictive Analytics & ML
W3
Causal Machine Learning
W4
Causal ML & Meta-Learners
W5
Advanced AI Architectures · A1 Due
W6
Introduction to Generative AI
W7
Prompt Engineering
W8
AI-Assisted Coding
W9
Assessment 2 · Group Presentation
W10
Agentic AI Frameworks
W11
Agentic AI Evaluation & Ethics
W12
AI-Driven Frameworks in Business
Why This Subject Matters 04 / 07

"AI is no longer a specialist skill — it is the foundation of competitive advantage. The analysts who thrive will be those who can build, deploy, and critique AI systems."

Career Relevance

AI programming is the core skill employers now expect

From customer churn prediction to marketing automation, businesses need graduates who can move beyond dashboards — building AI applications that directly drive decisions and measurable outcomes.

Beyond Correlation

Causal inference: knowing why, not just what

This subject goes further than most analytics courses. You will learn causal machine learning — enabling you to evaluate whether an intervention actually caused an outcome, not just whether it correlated with one.

Generative AI Literacy

Use and critique GenAI as a professional tool

You will use Large Language Models, prompt engineering, and AI-assisted coding as integral parts of your analytics workflow — and learn to evaluate their limitations, biases, and ethical implications.

Future-Proofing

Agentic AI: the next frontier in business automation

The course culminates in agentic AI frameworks — autonomous systems that plan and act across multi-step workflows. Understanding these positions you at the cutting edge of how AI is transforming enterprise operations.

Assessment Structure 05 / 07
ASSESSMENT 01 · WEEK 5 Predictive & Prescriptive Analytics for Business 25%
Type Individual Project — Business Report (1,200 words)
GenAI Prohibited (Level 1)

Run a provided Colab notebook for a SaaS customer retention scenario. Use LightGBM, TFT forecasting, SHAP, and EconML causal analysis — then write a professional business report with your findings.

ASSESSMENT 02 · WEEK 9 Generative AI for Predictive Analysis 35%
Type Team Project (groups of 4–5) + In-class Presentation
GenAI Compulsory (Level 3)

Analyse a social media dataset, conduct external research, and use generative AI to produce a marketing strategy complete with visual, video, and audio creative assets. Present live in class.

ASSESSMENT 03 · WEEK 13 Advanced AI Analytics Project 40%
Type Individual — Via Turnitin
GenAI Optional (Level 2)

Apply the full AI analytics workflow to a real-world business problem of your choosing. Demonstrate mastery across all four learning outcomes — from data sourcing through to advanced business insights.

A1: GenAI entirely prohibited. All analysis must reflect your own reasoning and computation.
A2: GenAI is compulsory — you are assessed on how effectively you harness and critique it.
A3: GenAI optional but must be referenced with all prompts documented in an appendix.
Software & Tools 06 / 07
Core Environment

Python on Google Colab

All analysis runs in browser-based Jupyter notebooks — no local installation required. Pre-built notebooks are provided for each assessment, allowing you to focus on interpretation and business insight rather than setup.

Predictive & Causal ML

LightGBM · EconML · SHAP

LightGBM for high-performance churn prediction; EconML for causal inference and treatment effect estimation (ATE & CATE); SHAP for explainable AI — understanding why the model made each prediction.

Deep Learning & Forecasting

Temporal Fusion Transformer · NeuralProphet

State-of-the-art sequence models for multi-horizon business forecasting. TFT handles complex temporal dependencies across multiple variables — used in Assessment 1 for revenue forecasting in a SaaS context.

Generative AI & Agentic Tools

Google Gemini API · ChromaDB · RAG

Hands-on experience with large language model APIs for content generation and prompt engineering. ChromaDB and RAG pipelines for knowledge-grounded AI. Agentic frameworks for multi-step autonomous workflows.

What to Expect & How to Succeed 07 / 07

What you will do each week

  • Attend 3-hour workshops combining theory, live coding demonstrations, and applied exercises in Python
  • Work with real-world datasets from SaaS, marketing, finance, and environmental contexts
  • Collaborate with AI tools as a co-analyst — the "vibe coding" approach, not rote programming
  • Translate technical model outputs into executive-level business recommendations
  • Build progressively from predictive ML through causal inference, GenAI, and agentic systems
Teaching Philosophy "You are not learning to code from scratch — you are learning to direct AI to solve real business problems. The insight is the product."

What distinguishes strong work

  • Grounding every recommendation in specific evidence from your analysis — no generic business statements
  • Demonstrating original thought: the marker distinguishes your reasoning from AI-generated filler
  • Connecting causal findings to actionable interventions — not just describing correlations
  • Using SHAP, ATE, and CATE outputs to make segment-specific, evidence-based recommendations
  • Professional report structure with compelling narrative, appropriate visuals, and Harvard referencing

Over-reliance on AI-generated content will be penalised across all assessments. Uploading the wrong file format incurs a project management penalty. Late submissions: 5% per day (1–9 days), 50% deduction (10–14 days), zero after 14 days.

← → arrow keys