引導式測驗 · 硬 等級
線上和離線功能服務偏差測驗
練習識別歷史訓練資料與即時請求之間的功能服務偏差、時間點洩漏以及新鮮度不符。
問題 1 的 8
什麼是訓練/服務偏誤?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 什麼是訓練/服務偏誤?
- 當模型在 GPU 上訓練但在 CPU 上運行時
- 當模型太大而無法容納在記憶體中時
- 當訓練期間離線計算的特徵與生產中線上提供的特徵不同時
- 當訓練時間比預期長時
- When building a historical training row, which feature timestamps should a point-in-time join allow?
- Values available at or before that row’s prediction time
- Values recorded only after the outcome
- The latest values regardless of historical time
- Only values from the next calendar month
- 下列哪一項是導致生產中離線精度過高而崩潰的典型原因?
- 使用的訓練樣本太少
- 在比服務更快的機器上訓練
- 將特徵儲存在資料庫中
- 資料外洩,訓練使用預測時不可用的信息
- A logged live feature distribution differs from training. What should the feature-serving team infer first?
- The serving code is certainly defective
- There is a mismatch to investigate; it may be drift or serving skew
- The feature has no predictive value
- The model must be running on different hardware
- 為什麼像「過去一小時的訂單」這樣的快取線上功能存在偏差風險?
- 快取的值可能會過時,並且不再與訓練中使用的新計算值相符
- 快取總是可以提高模型的準確性
- 快取使得該功能無法離線計算
- 快取的特徵不能是數字
- Why share one feature definition across batch training and online serving?
- To guarantee every cached value is fresh
- To eliminate changes in incoming populations
- To make timestamp checks unnecessary
- To reduce differences caused by separate transformation implementations
- A transaction model uses a chargeback flag recorded days after purchase. Why is its offline feature join invalid?
- The flag is categorical rather than numerical
- The flag was unavailable when the purchase prediction was made
- Chargeback flags cannot be stored historically
- Only GPU models may use transaction features
- Training recomputes a one-hour order count, but serving reads a ten-minute-old cached count. Which check targets this skew?
- Increase the number of model parameters
- Remove all timestamps from the feature store
- Compare counts for matching entities and times while recording cache freshness
- Switch both paths to a different programming language