PMGM7023 AI-Powered Management Analytics
The Complete Exam Bible · PMGM7023 Overview
- The University of Hong Kong
- Postgraduate
- Ten teaching sessions
- Four graded components
- Open book final exam
What this course actually trains
PMGM7023 is a postgraduate course in AI-powered management analytics at The University of Hong Kong, taught in the Management and Strategy area of the Faculty of Business and Economics.
- Assessed by four components A 40% open-book multiple-choice final exam, a 30% team report, 20% for tutorial Markdown files and 10% participation.
- Hardest step Deciding what one row of the data represents before any total is calculated or compared.
- Tool you must use GitHub Copilot CLI: the course states that all coursework is completed with it.
- Cheapest marks available Submitting each tutorial file on time, since a late file automatically receives No Record.
- Watch on the project Nine cumulative deduction lines, two of which cost twenty points and cannot be fixed after submission.
How PMGM7023 is assessed
| Component | Weight | Format |
|---|---|---|
| Final Exam | 40% | Open-book multiple-choice examination held in the final session, in the usual lecture slot; no make-up session and no electronic devices permitted |
| Team Analytic Project | 30% | One written report as an assigned team, with no presentation; body of 3,500 words or fewer plus a cover-page executive summary of 250 words or fewer; graded on three dimensions of fifty points each |
| Markdown Files | 20% | Tutorial exercises completed with Copilot CLI, saved as Markdown and submitted to Moodle; graded Plus, Check or No Record, with late submissions receiving No Record |
| Class Participation | 10% | Questions asked and answered, votes, quizzes and work handed in through the course platforms, gathered into one Plus, Check or No Record entry each session |
The four published components total 100%, and the syllabus states them as points as well as percentages: 200, 150, 100 and 50 out of 500. The grade table is headed as tentative, so confirm the current position on Moodle before relying on a weight for planning. Hurdle requirements are not stated in the course materials available here, so none is claimed in either direction. The team project carries a separate published deduction table, applied cumulatively after the three rubric ratings are summed, and a late-submission schedule of 10% up to one day, 20% beyond that but before the project debriefing, and 100% after the debriefing.
Assessment structure
Segment widths reproduce the published percentage weights and total 100%.
Current PMGM7023 dates
| Date | Item | Control |
|---|---|---|
| 7 September 2026 | Cluster registration form due | Submitted by one member of each cluster, due 23:59. |
| 7 October 2026 | Team project submission | One group member submits to the Moodle drop box by 14:00; the project briefing states only that the deadline will be announced on Moodle. |
| 10 October 2026 | In-class final examination | Session ten, during the scheduled lecture time. |
Dates are as published in Dates are taken from the course Moodle pages and the published schedule for this offering.. Confirm exact deadlines and submission settings in the live LMS.
What PMGM7023 covers
Twelve source-led chapters move from directing analytical work, through the vocabulary of the system you are directing, to collecting evidence you can defend and the assessed deliverable.
Managing an AI Analyst
Separate advice from artifacts and decide which form of help a task needs02What One Row Represents
Fix the unit of analysis, then recount before any total reaches a decision03The Analytics Workflow and Its Four Questions
Route a request into descriptive, diagnostic, predictive or prescriptive work04Human Judgment and Agent Execution
Write a brief with an objective, a boundary, a checkpoint and an acceptance test05Prompts, Context and the Model Engine
Use the standing instruction, the finite window and the sampling setting correctly06Evidence, Tools and Control in AI Systems
Diagnose an unsupported claim by layer and name the enforceable repair07Working Inside GitHub Copilot CLI
Set the trusted folder and permission mode, then keep the session legible08Specifying and Sourcing the Data You Need
Write the six-line collection contract and aggregate before you join09Web Scraping Within the Rules
Clear three permission checks, then pick the collection move that fits10Data Traps and Defensible Descriptive Claims
Repair a claim by naming the concern, the missing information and the limit11Cleaning a Real Dataset With a Supervised Agent
Profile, decide, execute, re-profile and report what the cleaning changed12The Team Analytic Project
Place a draft in the rubric bands and clear the nine deduction linesIts own syllabus is explicit that it is not designed for technicians but for future managers developing data literacy, and that no prior programming or analytics knowledge is required.
Ten sessions pair about two hours of lecture with about one hour of hands-on tutorial work in GitHub Copilot CLI, and the course states that for consistency and fairness all coursework must be completed with that tool.
The skill being built is direction rather than execution.
You learn to state a question precisely enough that an analysis can answer it, to acquire data that genuinely bears on it, to recognise when an output is confident and wrong, and to say what should happen next.
The opening session makes the point with a monitoring report whose arithmetic is perfect and whose headline is wrong, because several recorded contacts about one event were counted as several events.
How the sessions are organised
The first session covers managing an AI analyst: the progression from records to judgment, the difference between a conversation that returns advice and a supervised agent that returns files you can inspect, the six-decision analytics workflow, and the four question types that decide which analysis is relevant at all.
The second builds a working vocabulary in five layers, from what the system receives through the engine that generates the response, the evidence that supports it, the interfaces that let it act, and the controls that limit it.
The third session turns a management question into evidence: a six-line collection contract, eight families of data source, the discipline of aggregating every source to one analysis unit before joining, and the checks that separate genuine data from simulated data.
Its tutorial covers web scraping, including three permission checks that must all pass before any collection begins.
The fourth session is a clinic on data traps, covering sampling and nonresponse, measurement validity, descriptive summaries and denominators, and missing values and outliers, followed by a tutorial that cleans a deliberately messy dataset and reports what changed.
Later sessions listed in the published schedule move into survey analytics, hypothesis testing, measurement theory, regression and complex data, closing with an integrated framework, the project debriefing and the examination.
How it is assessed
Four graded components and nothing else.
The final examination is worth 40% and is an open-book multiple-choice paper held in the final session, in the usual lecture slot, with no make-up session and no electronic devices permitted. The team analytic project is worth 30% and is one written report with no presentation, judged on three dimensions of fifty points each.
Markdown files from the tutorials are worth 20% and are graded Plus, Check or No Record, with late submissions automatically receiving No Record. Class participation is worth 10% and is recorded session by session.
The project carries its own arithmetic.
Its body must be 3,500 words or fewer, its cover-page executive summary 250 words or fewer, and it must use at least two academic citations placed inside the body and attached to specific arguments.
Nine published deduction lines apply cumulatively: six formatting requirements at five points each, the citation requirement at ten, and twenty points each for data that are not genuine and for findings that cannot be reproduced from the submitted data and workflow.
A submission one day late or less costs 10%, later than that but still before the debriefing session costs 20%, and once the debriefing has passed the work receives nothing.
Where marks are most often lost
Three places, none of which is analytical skill. The first is the unit of analysis: a technique applied to the wrong row definition gives a precise answer to a question nobody asked.
The second is the denominator: a change is only large or small against a baseline, and a rate without its count can describe one person.
The third is format compliance on the project, where a team can lose a quarter of a performance band to word counts and file types without a single weakness in the argument.
How to use this guide
Each chapter takes one part of a session, names the decision it teaches, works one case through to a finished answer rather than describing what an answer would contain, and gives two prompts to write yourself.
Worked cases here are ours, built on new settings and new numbers, so that they train the method instead of the recognition of a familiar example. The closing chapters are a mixed practice set in the shape the examination uses and a pre-examination checklist. Confirm every operational detail, including deadlines and any current requirement, on the course Moodle page.
Audit a unit before trusting a total
- 3State what one row of the file records, and what unit the claim needs.
- 3Recount on the second unit and report both figures.
- 2Say which number travels to the decision and why the other does not.
Key terms
- Row Grain
- Row grain is the statement of what one row of a dataset represents, such as one contact or one completed event. It has to be fixed before any count, rate or comparison can be interpreted.
- Information Boundary
- Information boundary is the set of facts available to whoever or whatever is calculating. Moving it, by supplying context an export omitted, changes the answer without changing the arithmetic.
- Descriptive Analytics
- Descriptive analytics summarises what happened, covering size, timing, distribution, concentration and segments. It establishes the pattern but cannot on its own establish a cause.
- Diagnostic Analytics
- Diagnostic analytics tests rival explanations for an observed pattern. Each rival usually needs a different comparison, so the data required follows from which explanation is being tested.
- Prescriptive Analytics
- Prescriptive analytics chooses an action under constraints, weighing feasibility, cost and consequence. It requires information about options and ownership that no dataset contains.
- Retrieval-Augmented Generation
- Retrieval-augmented generation is a question-time process that searches an approved source collection, adds the relevant passages to the model's context, and asks it to answer from those passages.
- Hallucination
- Hallucination is fluent output stating something without adequate support from the input, the evidence supplied or reliable knowledge. It is detected by asking where the support is, not by reading for confidence.
- Guardrail
- Guardrail is a rule, filter, permission, validation or halt that is actually enforced on an AI system. An instruction to be careful is not one, because nothing enforces it.
- Context Window
- Context window is the finite amount of information a model can use for the current response. Anything falling outside it cannot be used for that answer, whatever its importance earlier.
- Survivorship Bias
- Survivorship bias is the distortion that arises when only cases that persisted can be observed. It is repaired by naming the cases that failed, withdrew or vanished and never reached the file.
- Measurement Validity
- Measurement validity is the question of whether a recorded number captures the concept it is meant to capture. It fails through proxy, outcome and definition mismatches.
- Winsorization
- Winsorization is capping verified extreme values at a stated limit rather than removing the cases. It requires the limits to be set once on the original data and the number of changed values to be reported.
PMGM7023 FAQ
Is the final exam open book?
Yes. The course materials describe an open-book examination made of multiple-choice questions with one correct answer each, held in the final session, in the usual lecture slot. Permitted books and printed materials may be brought in, electronic devices are not allowed, and no make-up session is offered. Because it is open book, preparation is better spent on a short navigable summary per session than on volume.
How is the team analytic project graded?
On three dimensions worth fifty points each, giving 150 before deductions: the research question, data and methods, and results and recommended actions. Each dimension is rated at one of four behaviour-anchored levels worth 50, 40, 30 or 20 points. Deductions are then applied cumulatively from a published list, and lateness costs 10%, then 20%, then the whole mark, depending on how far past the deadline the work arrives.
What happens if a tutorial Markdown file is late?
It automatically receives No Record. Tutorial exercises are completed with Copilot CLI, saved as a Markdown file and submitted to Moodle by the announced deadline, then graded Plus, Check or No Record. There is no partial credit for lateness, which makes submitting complete work on time the cheapest marks in the course. Check your class day, because the deadline is one day after your own tutorial.
Why does this course keep asking what one row represents?
Because a calculation over the wrong unit is precise and wrong. Several recorded contacts about a single event will be counted as several events unless the relationship between the rows is supplied, and every later technique inherits whatever unit the data arrived in. Writing the unit sentence before the total is the cheapest error check available on any dataset.
Can my team scrape any public website for the project?
No. Three checks must all pass first: the content must be reachable without logging in or paying, the site's terms must not prohibit automated access, and the site's crawler instructions must not disallow your target path. A single failure ends the collection for that path. Record all three verdicts with the date checked, since the project asks for the source, the URLs, the collection dates and the procedure.
How should missing values be handled?
By first asking why they are missing. A gap unrelated to anything recorded can be deleted or filled simply; a gap predictable from something you did observe should be predicted from those fields rather than filled with one average; a gap that may depend on the missing value itself has no automatic fix, so the analysis is reported both ways and the difference stated as a limit. A blank is never automatically a zero.
Do I need programming experience for this course?
The syllabus states that the course does not require prior knowledge of programming or data analytics and is designed for future managers rather than technicians. Tutorials are run through GitHub Copilot CLI in plain English, and the course states that all coursework must be completed with that tool. What is assessed is whether you can specify the work, check the output and own the decision.
How to study for the exam
Work one session at a time and finish each with a one-page summary carrying the decision that session teaches, the two or three distinctions it turns on, and the trap it warns about. Practise routing unseen requests into the four question types and diagnosing described failures by system layer, since those are the judgements an open-book paper can still test.
Keep every tutorial file complete and submitted on time, and run the project deduction list as a checklist a week before the deadline rather than from memory.
Your AI Management tutor for PMGM7023
Stuck on a hard PMGM7023 question? Sia is AskSia’s AI Management tutor — ask any PMGM7023 AI-Powered Management Analytics question and get a clear, step-by-step explanation grounded in how the course is actually taught and assessed. Read this whole study guide free, then take your hardest questions to Sia.
