Quiz collegato alla guida · Difficile Livello
Point-in-Time Correct Feature Joins Quiz
Understand event-time joins, TTL, late-created corrections, future-feature leakage, and why point-in-time joins alone cannot guarantee a clean dataset.
Domanda 1 di 8
Quale problema previene una giunzione corretta al punto temporale?
Anteprima di ogni domanda8 domande
Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.
- Quale problema previene una giunzione corretta al punto temporale?
- Joining feature rows whose event timestamps are later than the example’s decision timestamp
- Slow query performance on large tables
- Duplicate rows appearing in a feature table
- Features being stored in the wrong file format
- Perché addestrare un modello di abbandono su una funzionalità 'acquisti totali per l'intera durata' calcolata dopo la data di abbandono sarebbe un problema?
- It's not a problem, since it improves accuracy
- It would include purchases the customer made after already churning, which wouldn't be known at prediction time
- Lifetime purchase counts are always inaccurate
- It duplicates the label column
- Oltre a una chiave di entità, quale timestamp consente a una ricerca di funzionalità storica di sapere quale valore di tempo dell'evento recuperare?
- The time the training job starts
- The date the model was published
- A feature event timestamp and an entity-row decision timestamp
- The current wall-clock time only
- Per ciascuna riga etichettata, quale valore di funzionalità seleziona una giunzione as-of corretta?
- The feature value from exactly one year before the label
- Any feature value regardless of timestamp
- The average of all historical feature values
- The most recent feature value at or before the label's timestamp
- Quale errore descrive la guida come giunzione su uno snapshot attuale di una tabella di funzionalità?
- It silently includes feature updates that happened after the labeled event
- It correctly reflects historical state
- It removes all timestamp information from the join
- It only works for numeric features
- How do a feature event timestamp and a created or ingestion timestamp differ?
- They are always identical in practice
- Event time records when the underlying event happened; created time records when the feature row was created or became available
- Ingestion timestamp only applies to streaming data, never batch data
- Event timestamp is set by the feature store automatically and cannot be changed
- According to the guide, how is an as-of join commonly implemented at scale?
- By manually inspecting each row in a spreadsheet
- By deleting all historical feature versions except the latest
- With a window function partitioned by entity key and ordered by feature timestamp, or dedicated feature store SDK support
- By running the join only on a random sample of rows
- According to the guide, what is one limitation of a point-in-time join?
- It always removes every possible form of leakage
- It replaces the need for entity keys
- It automatically fixes late-arriving data in every store
- It cannot detect every future-derived feature or incorrect label cutoff