第 2 / 5 页
非代码面试题
显示 20 / 82 道匹配题目
答题状态：未尝试未正确已正确
ID题目领域难度题型进度权限
2667Why Class Stratification Is Not Enough for Repeated EntitiesWhy can class-stratified cross-validation still fail badly when the same issuer appears many times and issuer identity carries predictive information?机器学习简单essay未尝试免费2668Why Embargo Matters Even With Backward-Looking FeaturesSuppose features use only past prices, yet labels depend on future returns over an event window. Why can an embargo still be necessary around the validation block?机器学习中等essay未尝试面试订阅2669Why Purging and Embargo Solve Different ProblemsWhy is purging not the same thing as embargoing in time-series validation?机器学习中等essay未尝试面试订阅2670Why the Best CV Design Depends on the Deployment UnitWhy should the fold rule mirror the unit on which the model will actually generalize in production?机器学习困难essay未尝试面试订阅4341Confusion-Matrix Metrics 1At a fixed threshold, prevalence is 20%, TPR is 80%, and FPR is 10%. What precision does that imply?机器学习简单数值题未尝试面试订阅4342Confusion-Matrix Metrics 2A fraud model keeps TPR = 0.90 and FPR = 0.03 when deployed into a market where prevalence falls from 10% to 2%. What precision should you now expect at the same threshold?机器学习简单数值题未尝试面试订阅4343Confusion-Matrix Metrics 3Predicted probabilities are [0.8, 0.6, 0.3, 0.1] and labels are [1, 0, 1, 0]. What is the Brier score?机器学习简单数值题未尝试面试订阅4344Confusion-Matrix Metrics 4For expected calibration error with equal sample weighting, you have two nonempty bins. Bin A has probabilities [0.2, 0.3] and labels [0, 1]. Bin B has probabilities [0.8, 0.9] and labels [1, 1]. Using ECE = sum over bins of (bin fraction)*|avg confidence - accuracy|, what ECE do you get?机器学习简单数值题未尝试面试订阅4345Confusion-Matrix Metrics 5A model assigns an average predicted probability of 0.18 to a bucket containing 200 names. If the model is calibrated, how many positives should you expect in that bucket on average?机器学习简单数值题未尝试面试订阅4346Brier Score Snapshot 1At one threshold, prevalence is 5%, TPR is 80%, and FPR is 10%. What PR-space point (recall, precision) corresponds to that ROC-space operating point?机器学习中等数值题未尝试面试订阅4347Brier Score Snapshot 2Across 500 cases, a calibrated model has mean predicted probability 0.12. How many positives should you expect in total?机器学习中等数值题未尝试面试订阅4348Brier Score Snapshot 3On a validation set, the model's mean predicted probability is 9% but the observed positive rate is 6%. What calibration-in-the-large error does that imply?机器学习中等数值题未尝试面试订阅4349Brier Score Snapshot 4A thresholding rule is used on a universe where prevalence is 10%, TPR is 70%, and FPR is 5%. A false negative costs 4 units and a false positive costs 1 unit. What is the expected misclassification cost per case?机器学习中等数值题未尝试面试订阅4350Brier Score Snapshot 5A calibrated bucket contains 80 names with average predicted probability 0.35. If you actually observe 20 positives, what empirical positive rate does that bucket realize, and by how many percentage points is it under the average prediction?机器学习中等数值题未尝试面试订阅4351Asymmetric Threshold Choice 1Three candidate thresholds on the same classifier yield t=0.3 -> FP=18, FN=4; t=0.5 -> FP=9, FN=7; t=0.7 -> FP=4, FN=14. If one false negative costs 5 units and one false positive costs 1 unit(s), which threshold minimizes expected classification cost over this sample?机器学习中等数值题未尝试面试订阅4356Trade Ranking Versus Probability QualityModel A has slightly higher ROC AUC, but its probabilities are visibly overconfident; Model B has slightly lower ROC AUC but much better calibration. If you need a probability to size positions according to expected payoff, which model is usually safer?机器学习中等essay未尝试面试订阅4357Severe Imbalance Metric ChoiceYou are screening rare fraud cases with a base rate below 1%. Why is PR analysis usually more informative than ROC analysis for the operational discussion?机器学习中等essay未尝试面试订阅4358Same AUC Different ReliabilityTwo models have essentially the same ROC AUC. One is well calibrated, the other places most probabilities near 0 or 1. What should be your first concern before picking the latter?机器学习中等essay未尝试面试订阅4359Thresholds Need ContextWhy is it a mistake to ask for the 'best threshold' without specifying a cost ratio or downstream resource constraint?机器学习中等essay未尝试面试订阅4360Calibration After ShiftA model was calibrated on last year's data, but the event base rate has clearly shifted this year. What is the first calibration question you should revisit?机器学习中等essay未尝试面试订阅