SOST10031 Chap.10 Data Science in Practice and Portfolio Decisions
Data Science in Practice and Portfolio Decisions
Data Science in Practice and Portfolio Decisions brings the module together in timetable week 12, when the seminar turns to portfolio decisions.
SOST10031 is assessed entirely by an individual Data Science Portfolio of 2,000 words, worth 100% and due on Friday 11 December 2026 at 17:00. The chapter reconciles the two official descriptions of that task: the outline's three elements of annotated analysis, critical reflection and data story, and the Canvas framing of Part A, a guided analysis of a supplied Quarto file, and Part B, an investigation proposal.
It maps each of the six published marking criteria to a place in the portfolio, lays out the formative plan due on 30 October, and explains what the word count excludes. A model plan shows how a feasible question, a countable check and a material limitation fit together, and the closing tasks rehearse narrowing an infeasible question and preparing a reproducible submission.
What this chapter covers
- 01
Two official descriptions of the portfolio
- 02
The 2,000-word budget and its exclusions
- 03
Six published marking criteria
- 04
The five elements of the formative plan
- 05
Key dates from first lecture to deadline
- 06
Checked use of Copilot in Part A
- 07
Independent sources in both parts
- 08
Reproducible submission of source and PDF
Worked example · free
Check a draft against the 2,000-word budget
- 1Exclude the R code and the reference list, which sit outside the count.
- 1Counted words: 1,620 + 540 = 2,160, which is 2,160 − 2,000 = 160 over the maximum.
- 1Compare with the planning guide: Part A is 220 above its suggested 1,400 while Part B is 60 below its suggested 600.
- 1Cut about 220 words from Part A, for instance repeated numbers already visible in outputs, and add up to 60 to Part B so it reaches about 600.
Key terms
- Guided analysis
- Part A of the portfolio: a checked analysis using a supplied Quarto file, with a small guided change, interpretation and a short explanation for a general reader.
- Investigation proposal
- Part B of the portfolio: a focused question of your own with a realistic plan, using one or both teaching datasets.
- Formative portfolio plan
- A 250-word practice plan that receives feedback but does not count towards the module mark.
- Critical reflection
- The portfolio element that evaluates data quality, analytical decisions, limitations, ethical issues and the contribution of Copilot.
Data Science in Practice and Portfolio Decisions FAQ
Which parts of the semester's work feed the one marked task?
Everything converges on a single individual Data Science Portfolio of 2,000 words carrying the whole module mark. Seminar notes, guided R exercises and the 250-word formative plan prepare it; the plan returns written feedback after reading week while carrying no weight, so it acts as a rehearsal for Part B.
Which items sit outside the 2,000-word count?
Code chunks, the tables and graphs R produces, and the reference list do not count. Roughly 1,400 words for the guided analysis and 600 for the proposal is a planning suggestion, so shift words between the parts if your argument needs it, provided the total stays within the limit.
Do I have to write R code for the portfolio?
You are not expected to write R code from scratch. Part A asks you to make small guided changes to a supplied Quarto file and explain their effect, and Part B is a plan that needs no new code.
When is the portfolio due and how is it submitted?
The deadline is Friday 11 December 2026 at 17:00. You submit electronically through the designated point in the Canvas Assignments section, including the completed Quarto source file and its rendered PDF as the final brief specifies.
Assessment move
Work backwards from Friday 11 December. Two weeks out, render the supplied analysis, make the guided change and write down how you checked the output. Ten days out, draft Part A in plain language and ask Copilot to critique your interpretation, logging each suggestion you accept or reject and why.
One week out, finalise Part B using your formative feedback: keep what worked, clarify what was vague and act on the development point. Check every paragraph against the six published criteria and confirm that each part cites at least one source you found yourself. Three days out, count only the words that count, cut repeated numbers first and keep the rough 1,400 and 600 balance.
On the last day, render again from a fresh session, compare several numbers in the text against the PDF, and submit both the source file and the PDF.
Working through Data Science in Practice and Portfolio Decisions in SOST10031? Sia is AskSia’s AI Computer Science tutor — ask any SOST10031 Data Science in Practice and Portfolio Decisions question and get a clear, step-by-step explanation grounded in how SOST10031 is taught and assessed. Read this chapter free, then take your hardest questions to Sia.