Daily Pizza Output Variance

This quant interview question is about modeling total output when many similar, noisy contributors are aggregated. It lives squarely in the expected value and variance toolkit that shows up all over quant prep: production across workers, trade counts across days, or PnL across strategies. You are asked to reason about the overall randomness of a sum when each component is uncertain but behaves in the same way.

It trains your understanding of variance for sums of independent random variables, and how scale and diversification affect overall risk. You practice moving between individual-level uncertainty and portfolio-level uncertainty, developing intuition for how randomness combines when many independent sources are involved.

This matters for quant interviews because the exact same reasoning underlies risk aggregation, volatility modeling, and portfolio construction. Top trading firms expect you to handle such core probability ideas quickly and confidently in live interviews.

What it tests

When dealing with sums of independent random variables, the key structure is that variances add, not standard deviations. This is because variance measures the expected squared deviation from the mean, and for independent variables, the cross-terms vanish, leaving the sum of individual variances. The standard deviation of the sum is then the square root of this total variance, which means it grows with the square root of the number of terms if the variables are identically distributed. This principle holds regardless of the distribution's shape, as long as independence is maintained. The intuition is that while each variable's fluctuations can go in either direction, their combined spread grows more slowly than their total number, due to averaging out of independent noise.