Claude for Finance: Building a Live Merger Model with AI

Why It Matters

AI‑driven modeling dramatically speeds M&A analysis, but human oversight remains essential to ensure accuracy and strategic insight.

Key Takeaways

• Claude can auto‑populate merger model sheets from public filings.
• GameStop’s $125 per share, 50/50 cash‑stock offer values eBay at $56B.
• Model highlights massive dilution: GameStop shareholders own ~25% post‑deal.
• Projected $2 B synergies hinge on rapid integration of retail network.
• AI tools still need prompt engineering and data verification.

Summary

The episode showcases a live demonstration of Claude for Excel, an AI‑powered tool that builds a full‑blown merger model for the speculative GameStop acquisition of eBay. Hosts Deb Taylor and Graham Smith walk listeners through the deal’s headline terms—$125 per eBay share, a 50/50 cash‑stock mix, and a $56 billion valuation—while prompting Claude to assemble the spreadsheet, pull data from SEC filings, and generate pro‑forma calculations. Key insights emerge around the deal’s financing and ownership outcomes. GameStop, with roughly $10 billion in cash, would need to raise additional debt and issue a large block of new shares, leaving its existing shareholders with only about a quarter of the combined company. The model also flags the touted $2 billion annual synergies from using GameStop’s retail footprint as eBay’s fulfillment hub, and it highlights a modest premium relative to eBay’s pre‑announcement price, suggesting low market confidence. Throughout the session, the hosts note Claude’s practical quirks: the AI inserts source comments in cells, but its answers can vary and sometimes stall, underscoring the need for precise prompt engineering. They quote the AI’s own admission that it “doesn’t know” certain inputs and must be guided to fetch public data, illustrating both the promise and current limitations of generative tools in finance. The broader implication is clear: AI can compress weeks of manual modeling into minutes, offering a powerful productivity boost for investment banks and corporate finance teams. However, the demo also warns that analysts must still validate assumptions, manage dilution calculations, and interpret results, especially for high‑profile, unlikely deals like GameStop‑eBay.

Original Description

Can AI build a merger model from a single prompt?

In this episode, we put Claude for Excel to the test by asking it to construct a full accretion/dilution analysis from scratch — sources and uses, pro forma adjustments, synergy assumptions, share issuance, the lot.

The case study is GameStop's $56 billion bid for eBay, but the focus is on the workflow: how to prompt Claude effectively, where the tool excels, where it fails, and what investment banking analysts and associates need to know about using AI in real M&A work.

WTBD Newsletter:

https://webmail.wallstreetprep.com/whats-the-big-deal

Follow Us On Socials:

LinkedIn: https://www.linkedin.com/company/wall-street-prep/

Instagram: https://www.instagram.com/wallstreetprep/

Resources: https://linktr.ee/wallstreetprep

TIMESTAMPS

00:00 — Episode intro: What's the Big Deal?

00:33 — This week's focus: testing Claude for Excel on a live merger model

04:17 — Merger models explained: accretion, dilution and pro forma

06:28 — Pro forma defined: what it actually means

07:34 — Building a live merger model with Claude for Excel

09:49 — Claude's first output: what it got right and what it missed

15:17 — Sources and uses: correcting the cash assumption in real time

19:23 — The pro forma tab: combining the two businesses

22:31 — LTM and calendarisation: fiscal year alignment

27:05 — Running the model: stress-testing accretion/dilution

29:17 — Interest expense, tax rate and numerator adjustments

33:37 — Base case results: break even at best

35:38 — Key levers: synergies, consideration mix and share issuance

39:27 — Verdict on Claude for Excel: what AI can and cannot do in finance

48:35 — Sign-off

Topics covered:

→ Merger models explained: accretion, dilution, pro forma and why EPS impact matters

→ Sources and uses: how to structure deal financing in a model

→ LTM and calendarisation: aligning fiscal years across acquirer and target

→ Prompting Claude for Excel: what works and what does not

→ Where Claude saves analyst time: factual data sourcing, structure, first-pass build

→ Where Claude fails: modelling best practices, hardcoded assumptions, technical errors

→ Stress-testing synergies, consideration mix and interest expense in real time

→ AI in investment banking: powerful time saver or dangerous in the wrong hands?

Whether you are an analyst, associate, or preparing for an M&A interview, this is a practical demonstration of what AI can and cannot do in real finance workflows.

Why Wall Street Prep?

Wall Street Prep is the trusted training provider for the world's top investment banks, private equity firms, Fortune 1000 companies and business schools.

Our online training and instructor-led boot camps are direct adaptations of our corporate training, making Wall Street Prep the ideal choice for those looking to break into finance.

DISCLAIMER:

The information provided in this video is for educational and entertainment purposes only and does not constitute financial, investment, tax, or legal advice. Investing involves risk, and you may lose some or all of your capital.

Past performance is not indicative of future results. Please conduct your own due diligence or consult with a certified professional before making any financial decisions.