第 14 / 17 页
非代码面试题
显示 20 / 333 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
4401Close-to-Close LeakYou predict tomorrow's close-to-close return at today's close, but one feature uses today's official closing auction price finalized after the decision timestamp. Why is that a leakage problem?机器学习中等essay未尝试面试订阅4402Target Overlap TrapYou build a 5-day forward-return label every day and then use adjacent samples as if they were independent. What is the structural issue?机器学习中等essay未尝试面试订阅4403Rolling Mean That PeeksA feature at time t uses a rolling mean computed from t-19 through t+1. Why is that unacceptable even if it is only one extra day?机器学习中等essay未尝试面试订阅4404Cross-Sectional Residualization TimingWhy should factor residualization for a daily return feature use exposures known at the feature timestamp rather than exposures estimated using later returns?机器学习中等essay未尝试面试订阅4405Corporate Action MisalignmentA feature uses raw prices while the target uses split-adjusted future returns. What problem can that create?机器学习中等essay未尝试面试订阅4406Longer Horizon, More SmoothingIf you lengthen a forward-return label from 1 day to 20 days while sampling daily, what happens to overlap and effective sample independence?机器学习中等essay未尝试面试订阅4407Residual Feature DriftWhy can a residualized return feature that looked stable in-sample become unstable after a regime shift?机器学习中等essay未尝试面试订阅4408Normalization Window LengthIf you shorten the rolling window used to z-score a return feature, how does the feature usually respond to recent shocks?机器学习中等essay未尝试面试订阅4409Raw Returns Versus Scaled ReturnsWhy can a model trained on raw multi-asset returns misallocate attention across assets compared with standardized return features?机器学习中等essay未尝试面试订阅4410Sampling FrequencyIf you downsample from daily to weekly observations when using medium-horizon return features, what usually happens to overlap and microstructure noise?机器学习中等essay未尝试面试订阅4411Before Adding A FeatureBefore adding a new return-based feature to your model, what is the first alignment question you should ask?机器学习中等essay未尝试面试订阅4412Before ResidualizingWhat should you clarify before residualizing returns against factors and treating the residual as a new feature?机器学习中等essay未尝试面试订阅4413Before Expanding HorizonWhat should you check first before lengthening a forward-return horizon because the 1-day target looks noisy?机器学习中等essay未尝试面试订阅4414Before StandardizingBefore standardizing a return feature, what should you check about the universe you are mixing?机器学习中等essay未尝试面试订阅4415Before Trusting Feature ImportanceA return feature looks very important in a trained model. What should you check first before concluding it captures genuine alpha?机器学习中等essay未尝试面试订阅4416Walk-Forward Tradable Coverage 1A rolling walk-forward scheme uses 24 months of training, then a 1-month embargo, then 6 months of testing, and advances by 6 months each time across 61 months of history. In each test block, the first 2 months are used only to warm up a trailing feature, so they are not tradable. How many tradable out-of-sample months do you score in total?机器学习简单数值题未尝试面试订阅4417Expanding Window Final Training Length 2An expanding-window walk-forward starts with 18 months of training, then uses a 1-month embargo and a 4-month test block, advancing by 4 months each round across 59 months of history. What is the training-window length in the last complete fold?机器学习简单数值题未尝试面试订阅4418Embargo Budget Across Folds 3A walk-forward backtest produces 7 complete folds, and the research protocol inserts a 3-day embargo between each training block and its following test block. How many calendar days are lost to embargo across the whole run?机器学习简单数值题未尝试面试订阅4419Average Training Length Under Expansion 4An expanding walk-forward starts with 12 months of training and then advances by 6 months for each of 5 complete test folds. What is the average training-window length used across the 5 folds?机器学习简单数值题未尝试面试订阅4420Latest Label-Safe Training Day 5A test block starts on day 121. Training labels are 5-day forward returns, and you also impose a 2-day embargo immediately before the test block. What is the latest training day whose full forward label still remains valid?机器学习简单数值题未尝试面试订阅