- [[bias-variance tradeoff]], [[model error decomposition theorem]] # Idea The number of **relevant** attributes constrains the number of **distinct categorizations**, and therefore the number of useful models. Although adding models improves accuracy (they have to, given the [[Condorcet paradox|Condorcet jury theorem]] and [[diversity prediction theorem]]), the [[marginal benefit]] of each additional model decreases after a handful of models. [[Page 2018 model thinker - what you need to know to make data work for you]] > Google found that using one interviewer to evaluate job candidates (instead of picking at random) increases the probability of an above-average hire from 50% to 74%, adding a second interviewer increases the probability to 81%, adding a third raises it to 84%, and using a fourth lifts it to 86%. Using twenty interviewers only increases the probability to a little over 90%. That evidence suggests a limit to the number of relevant ways of looking at potential hire. # References