Kumu / Corporate Finance

International Corporate Finance

The Performance Ratios project — AI + GitHub throughout: build a public portfolio repo, model a real company's financials, specify an analysis precisely enough for an AI to execute it — then judge whether the AI got it right.

Graduate · 6 stages 6 stages · 100% of project grade 45% of course grade Deliverable-only — no presentations

Stage 0 — get GitHub working, before the project

Every stage of this project is handed in by committing it to a public repository of your own, so the repository comes first — before the template, before the company memo, before any analysis. One sitting, once, and the rest of the term is about finance instead of tooling.

It comes in two parts: the account, then the workspace.

1

Part 1 — Get a GitHub account never used GitHub? start here

Create the account and learn the three verbs — add → commit → push. If you already have a GitHub account you can use that: sign in, add your hawaii.edu address, and go straight to part 2. If not, sign up with that hawaii.edu address — it is what unlocks GitHub Education.

account + mechanics
2

Part 2 — Set up your workspace

Directory skeleton, LLM-drafted bio & resume — your public professional home base.

5%Repo URL

Part 1 in full: the Git mechanics walkthrough

Start Here → Git mechanics walks the whole workflow once: local versus remote, add → commit → push in the desktop app and on the command line, editing files straight on github.com, and fixes for the mistakes everyone makes the first time. Read it before part 2 — the stage page assumes you can already save work to a repo, and does not re-teach the mechanics.

0 of 6 stages complete

The learning path — stages 1 to 5

Each stage produces a named artifact the next stage consumes. Work them in order — the chain is the point.

1

The Ratios Template

Understand the provided Excel architecture: tabs, color coding, and the named-range system everything else depends on.

20%.xlsx upload
2

Company Selection Memo

Pick your company, defend the choice like a senior analyst, and set falsifiable hypotheses. Grant instructor access.

10%.md memo
3

Populate the Financials

Enter two years of real statements, tie every number to the source filing, and watch the Ratios tab come alive.

20%.xlsx build
4

The Technical Specification

The central artifact: use an LLM to draft a spec so precise that another AI — with zero context — can execute your analysis.

20%.md spec
5

Analysis, Evaluation & Polish

The capstone: run your spec through an LLM, verify its numbers by hand, write the executive judgment only you can provide.

25%Repo URL

Practice first

Interactive lab

Ratio Lab

Two years of statements in, all six ratio categories out — with the balance-sheet check, startYear_* averaging, and a Du Pont decomposition validated against direct ROE. Mirrors performance-ratios-template.xlsx.

Field guide

AI Tools Lab

The field guide to coding LLMs: chat vs "code" tools, web vs desktop vs CLI, and why giving the AI your repo is the single biggest upgrade. Read it before your first AI build session.

The thread that ties it together

Stage 0 ── set up your public portfolio repo
   ↓
Stage 1 ── upload the ratios Excel template          models/templates/
   ↓
Stage 2 ── memo: choose & justify your company       docs/decisions/
   ↓            (instructor reviews via pull request)
Stage 3 ── populate template with real financials    models/builds/
   ↓
Stage 4 ── LLM drafts your technical spec            docs/specs/
   ↓            (one human-in-the-loop iteration, documented)
Stage 5 ── feed ONLY the spec to an LLM → verify,
           evaluate, correct → final analysis        deliverables/
           polish the repo → submit the URL

The finished repo is a portfolio piece — a URL you can put on LinkedIn that shows AI-assisted analysis, spec-driven design, and version-controlled professional work.

Skills you're actually building

SkillWhere it shows up
AI literacy & prompt engineeringDrafting with LLMs at Stages 0, 2, 4; evaluating LLM output at Stage 5; the prompt log throughout
Spec-driven designStage 4's core lesson: specifying work precisely is more valuable than executing it
GitHub & version controlEvery stage commits to your repo; PR-based feedback from Stage 2
Financial modelingNamed-range architecture (Stage 1), real-data population and tie-out (Stage 3)
Executive judgmentStage 5's verification table, LLM critique, and the investment thesis in your own voice

House rules (they're graded)