What problem does it solve? A single point-estimate DCF hides how much uncertainty sits behind the valuation. This Skill replaces two to four key drivers of a finished DCF with probability distributions, runs the same model thousands of times, and returns a full distribution of value — percentiles, the probability the value exceeds the market price, and the share of infeasible draws. ## Core Features & Use Cases - Probabilistic DCF simulation: Samples driver distributions (uniform, triangular, normal, lognormal, discrete) through inverse CDFs and re-runs the DCF engine per trial, with a mandatory seed for full reproducibility. - Correlated drivers via a common-factor model: Assign factor loadings so drivers like revenue growth and margin move together, with realized correlations reported against targets. - Scenario and percentile analysis: Price named discrete scenarios into a probability-weighted expected value, or locate a market price inside a published percentile table. - Use Case: Valuing an oil company where the oil price dominates — regress revenues on the oil price, simulate the oil price and target margin as correlated distributions, and report a 10th-to-90th percentile value range instead of a single number. ## Quick Start Run a Monte Carlo simulation on my completed DCF by distributing revenue growth and operating margin, then tell me where the current market price sits in the resulting value distribution.
