A back-test gives you one number, but how sure should you be of it? Bayesian inference answers with a whole range of plausible values instead of a single guess. This skill explains it in plain steps, with short checks (numbers you compute, steps you order, concepts you match) and finance examples: how a prior belief and a few days of results combine, why a strategy that won 7 days out of 10 is not yet proven, how to read a credible interval and make a decision from it, how a sampler explores a posterior that has no formula, why the average returns of many stocks should be pulled toward each other, and how to compare two models fairly. The capstone is a code lab where you write the sampler and the shrinkage yourself and use them on real stock returns.
Probability is expected (conditional probability, common distributions) and basic statistics helps. No Bayesian background is needed.
