DCF Valuation App explanation

DCF Valuation Application explanation video. #ai #finance AI Usage Disclosure Course: MGMT 490 — AI for Finance | Spring 2026 Project: DCF Corporate Valuation App Student: Jorge M. --- AI Tools Used: - Claude / Antigravity AI — AI coding assistant used throughout the project How AI Was Used App Development: AI: Generated Streamlit application code, helped debug errors, structured the DCF calculation logic Me: Defined project requirements, chose the app framework (Streamlit + Python), reviewed and validated all code Financial Modeling: AI: Assisted with implementing the DCF formulas in code Me: Selected the modeling approach (CAPM for cost of equity, Gordon Growth for terminal value), chose all default assumptions based on Apple's financials and industry data Assumptions & Inputs: AI: Provided reference data points for WACC components Me: Made final decisions on default values (10% WACC, 5% growth, 2.5% terminal growth) based on course material and financial theory Sensitivity Analysis: AI: Helped implement the 2D heatmap and data table Me: Defined which variables to test (WACC vs. terminal growth), interpreted results and investment implications Presentation Materials: AI: Assisted with drafting script and slide content Me: Reviewed, personalized, and will deliver the presentation in my own words Deployment: AI: Guided the Streamlit Cloud deployment process Me: Created the GitHub repository and deployed the app What I Learned: Through building this project, I deepened my understanding of: - How each WACC component (risk-free rate, beta, equity risk premium, cost of debt) connects to observable market data - Why DCF valuations are highly sensitive to discount rate and terminal growth assumptions - How sensitivity analysis transforms a single-point estimate into actionable investment insight - The practical workflow of building and deploying a data-driven financial tool