Double-Headed Coin After 10 Heads

This quant interview question is about interpreting unlikely streaks in a simple probabilistic model and asking what they say about the hidden mechanism that produced them. It sits at the core of conditional probability and Bayesian reasoning, framed in an intuitive, high-signal way that interviewers at top trading firms like to use for fast screening.

It trains your ability to update beliefs when new evidence arrives, a central skill in quant prep. You must distinguish prior odds from evidence, weigh competing hypotheses, and quantify how surprising an outcome is under each scenario. It reinforces disciplined thinking under uncertainty rather than gut feeling.

This matters for quant interviews because real trading and risk problems are structurally similar. You observe rare market patterns, infer which regime you are in, and reallocate capital accordingly. Firms want candidates who naturally think in these probabilistic, model-based terms.

What it tests

This problem class is governed by Bayesian inference, where you update your belief about an underlying cause (such as which type of coin you have) based on observed evidence (such as a sequence of coin flips). The key is that the likelihood of observing the evidence can be drastically different under different hypotheses, and Bayes' theorem formalizes how to combine your prior beliefs with the likelihood of the evidence to get a posterior belief. The pattern always involves weighing how surprising the evidence is under each possible scenario, not just how likely each scenario was before you saw the evidence. This is why rare events (like many consecutive heads) can strongly shift your belief toward a rare cause if that cause makes the evidence much more likely. The principle holds because probability is fundamentally about updating beliefs in light of new information, and Bayes' theorem is the unique, consistent way to do this.