Cuestionario vinculado a una guía · Medio Nivel

Bucles de retroalimentación en el cuestionario de sistemas ML

Rastree cómo las acciones del modelo afectan los resultados observados y los datos de capacitación futuros, e identifique salvaguardas contra el sesgo de selección y exposición.

Rutas de guía relacionadasBucles de retroalimentación en sistemas ML
Pregunta 1 de 8

How can a recommender create a feedback loop?

Vista previa de cada pregunta8 preguntas

Las respuestas y explicaciones aparecen a medida que realiza el cuestionario.

  1. How can a recommender create a feedback loop?
    • Its exposure choices affect clicks that later become training evidence
    • Its predictions are never stored
    • Its model weights are fixed
    • Its users cannot respond to recommendations
  2. Why may hiring outcomes be missing for applicants screened out by a model?
    • Their labels are always negative
    • They do not receive the downstream opportunity that generates an outcome
    • The model stores every outcome automatically
    • The feature schema removes labels
  3. What does recording which items were shown help distinguish?
    • A GPU failure from an API timeout
    • Training data from model parameters
    • Exposure opportunity from user preference evidence
    • A label from a feature name
  4. When can inverse-propensity evaluation be unreliable?
    • When the target policy matches the logging policy
    • When all propensities are recorded correctly
    • When randomized experiments have enough data
    • When the new policy chooses actions with no support in logged data
  5. Why monitor label coverage by score or group?
    • Coverage proves the model is fair
    • Observation rates may differ because the model routes cases differently
    • Scores are always outcomes
    • Every group must have identical labels
  6. Which data-collection strategy can reveal outcomes for less-shown alternatives?
    • Remove the need for logging
    • Guarantee every recommendation is relevant
    • Gather evidence about alternatives that a deterministic policy rarely shows
    • Make all users receive identical items
  7. Why might more training data fail to remove feedback-loop bias?
    • Bias is always random
    • Larger datasets cannot contain labels
    • Training never uses user interactions
    • New data may be generated by the same selective policy
  8. What kind of system property is a feedback loop?
    • A property of the deployed sociotechnical process and its data collection
    • Only a gradient calculation
    • A model architecture name
    • A feature scaling method