Final Project Report & Presentation Guide

This guide defines the expected structure, quality standards, and grading rubric for the final deliverables in Data Analysis with Spreadsheet Program.

1) Deliverables (Required)

• Final report (PDF): 2,000-2,500 words, professional structure.
• Excel workbook: cleaned data, analysis sheets, PivotTables, and final dashboard.
• Presentation slides: used for Week 15 presentation.
• 15-minute group presentation + 5-minute Q&A.

2) Recommended Report Organization

1. Introduction: Background -> Challenges -> Motivation

• Background: State the problem clearly and explain why this project/research is needed in this field.
• Challenges: Explain why related/comparison methods are not fully sufficient (or have limitations) for this specific problem context.
• Motivation for Proposed Methodology: Show how those gaps motivate your proposed analytical workflow/methodology.
• End the section with 3-5 research questions aligned with your proposed approach.

2. Related Work (with citations)

• Introduce key related/comparison methods used in the same or similar problem domain.
• Cite sources properly and summarize their strengths and limitations in your context.
• Explain which baseline/comparison methods you will use in your report and why.

3. Methodology (Dataset/Cohort + Proposed Method)

• Dataset / cohort population and characteristics: data source, sample size, unit of analysis, key variables, and inclusion/exclusion assumptions.
• Data preparation protocol: data quality issues found and cleaning decisions (Power Query / Excel steps), including rationale.
• Proposed method: clearly describe the analytical pipeline you propose (descriptive statistics, segmentation, PivotTables/visualization, and inferential/statistical analysis).
• Comparison design: specify baseline/comparison methods and explain why your proposed methodology is expected to perform better or be more suitable.
• Reproducibility requirements: formulas, filter criteria, sheet logic, and assumptions must be documented so another analyst can replicate the workflow.

4. Results and Visual Evidence

• Present key findings with numbered tables/figures and clear captions.
• Report both descriptive and inferential outputs where relevant (e.g., means, gaps, CI, p-values, regression coefficients).
• Include direct comparison against baseline/related methods and interpret why differences occur.
• Demonstrate dashboard evidence: which question each visual answers and what decision it supports.

5. Discussion and Recommendations

• Interpret findings in context of the original problem and stakeholder needs.
• Translate results into actionable recommendations with priority (short-term vs long-term).
• Discuss trade-offs and implementation feasibility (data availability, policy/process constraints).

6. Limitations and Conclusion

• State explicitly what the analysis can and cannot conclude.
• Describe data and method limitations honestly (bias, missing variables, assumptions, scope).
• Conclude with the main takeaway and concrete future improvements.

3) Title Writing Guide (Adapted for Excel Analytics)

Use this title pattern:

<Method> + <Task> + <Objective or Dataset/Target Entity>

• Question 1: What is the main method?
• Question 2: What task does it serve (descriptive analysis, segmentation, hypothesis testing, regression, dashboarding)?
• Question 3: Who is the target entity or audience receiving value from the analysis (e.g., faculty board, scholarship committee, program manager)?

Excel-course examples

• PivotTable-Based Segmentation for Identifying GPA Gaps Across Faculties in University Student Records
  (Method = PivotTable segmentation, Task = gap analysis, Objective/Target Entity = faculty managers)
• Regression and Dashboard Analysis for Explaining Academic Performance in the StudentRecords Dataset
  (Method = regression + dashboard, Task = explanatory analytics, Objective/Target Entity = academic advising team)
• Confidence-Interval and T-Test Evaluation of Program-Level GPA Differences for Curriculum Decision Support
  (Method = CI + t-test, Task = inferential comparison, Objective/Target Entity = curriculum committee)

4) Contribution-Driven Writing (Most Important)

Your contribution is the most important part of the report. It should appear in the Introduction and be reinforced in every major section.

How to state contribution from related-method limitations

Use this logic:

Limitation in related/comparison methods -> Gap -> Your contribution -> Evidence

• Limitation: What existing methods fail to handle well in your context?
• Gap: What specific analytical need is still unmet?
• Contribution: What do you introduce (workflow, model, dashboard logic, evaluation design) to address that gap?
• Evidence: What result proves the contribution (better metric, clearer segmentation, more actionable insight)?

Contribution statement template

“Existing approaches [limitation]. To address this gap, we propose [your method/workflow], which enables [practical objective]. Compared with [baseline], our approach achieves [evidence: metric/insight/actionability].”

How to repeat contribution in each section

• Introduction: State the contribution claim explicitly after motivation.
• Related Work: Position contribution against limitations of prior methods.
• Methodology: Show where contribution appears in your pipeline/design decisions.
• Results: Provide quantitative/visual evidence for each contribution claim.
• Discussion: Explain why the contribution matters for stakeholders and decisions.
• Conclusion: Restate contribution succinctly as the main takeaway.

5) Sample Papers (Read Before Writing)

Use the following papers as structural and writing references. You are not required to replicate their methods exactly; instead, learn how they formulate problem, gap, contribution, methodology, and evidence-based discussion.

• Machine learning approach to student performance prediction of online learning (PLOS ONE)
  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0299018
• Bayesian multiple membership multiple classification logistic regression model on student performance with random effects in university instructors and majors (PLOS ONE)
  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0227343
• Performance prediction using educational data mining techniques: a comparative study (Discover Education, Springer)
  https://link.springer.com/article/10.1007/s44217-025-00502-w
• Predicting GPA of University Students with Supervised Regression Machine Learning Models (Applied Sciences, MDPI)
  https://www.mdpi.com/2076-3417/12/17/8403

6) Writing and Visualization Standards

• Use declarative chart titles (state insight, not just variable names).
• Label all axes and include units.
• Reference every figure/table in text (e.g., "Figure 2 shows...").
• Avoid chartjunk: unnecessary 3D effects, clutter, weak color contrast.
• Keep dashboard filters consistent and functional (slicers/timelines).
• Write methods clearly enough that another student can reproduce the workflow in Excel.
• In discussion, include at least one limitation and one risk of misinterpretation.
• Use contribution-led topic sentences: each subsection should begin with the claim it contributes.

7) Presentation Structure (15 minutes)

• 2 min: Problem context and research questions
• 3 min: Data and methods
• 7 min: Key findings + dashboard walkthrough
• 3 min: Recommendations, limitations, conclusion

Every team member should contribute. Focus on interpretation and decisions, not only tool steps.

8) Evaluation Rubric (10-point scale)

9) Final Checklist Before Submission

• Report is complete (2,000-2,500 words) and logically structured.
• Report follows an IMRAD-like flow (Introduction, Methods, Results, Discussion/Conclusion).
• A clear contribution statement is present in Introduction and reinforced in Results/Conclusion.
• Contribution is derived from limitations of related/comparison methods (not only from intuition).
• All major claims are supported by charts/tables/statistical outputs.
• All figures and tables are numbered, captioned, and referenced in text.
• Methods are reproducible (clear Excel steps, formulas, filters, and assumptions).
• Discussion is honest about limitations and practical constraints.
• Dashboard is polished, interactive, and aligned with report findings.
• Excel workbook is organized and readable (sheet names, formulas, notes).
• Slides are concise and presentation-ready.

Back to schedule: Course Schedule