Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

AI Iṣeduro Systems adanwo

Review recommendation methods, collaborative and content filtering, matrix factorization, hybrid systems, and engagement risks.

Jẹmọ itọsọna awọn ọnaAI iṣeduro Systems
Ibeere 1 ti 8

Kini 'sisẹ iṣọpọ' dale lori lati ṣe awọn iṣeduro?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Kini 'sisẹ iṣọpọ' dale lori lati ṣe awọn iṣeduro?
    • Awọn awoṣe kọja ọpọlọpọ awọn olumulo pẹlu awọn itọwo ti o jọra
    • Apejuwe ọrọ ti nkan kọọkan nikan
    • Iye owo ọja naa
    • A ti o wa titi Olootu top-10 akojọ
  2. Sisẹ orisun akoonu ṣeduro awọn ohun kan nipataki nipasẹ:
    • Ayẹwo ID ti katalogi
    • Baramu awọn ẹya ohun kan si awọn ayanfẹ rẹ ti o ti kọja
    • Kika lapapọ agbaye tita
    • Béèrè awọn olumulo miiran lati dibo
  3. What did the Netflix Prize seek to improve by 10% over the Cinematch baseline?
    • Click-through rate for every recommended film
    • The number of films watched per user
    • Root mean squared error (RMSE) on the competition’s held-out ratings
    • A user’s average watch time on the service
  4. Ni iṣelọpọ matrix, awọn olumulo ati awọn ohun kan jẹ aṣoju bi:
    • Nikan bẹẹni/ko si awọn asia
    • Itele ọrọ agbeyewo
    • Awọn ọjọ kalẹnda
    • Awọn olutọpa ti 'awọn ifosiwewe wiwaba' pamọ
  5. What mechanism did the Deep Interest Network paper propose for modeling a user’s different interests across candidate ads?
    • A local activation unit that forms a candidate-specific interest representation
    • A fixed user vector that is identical for every candidate
    • A rule that selects only the most popular ad
    • A graph algorithm that proves every ad is relevant
  6. Oludamọran 'arabara' jẹ ọkan ti:
    • Nikan ṣiṣẹ lori ose
    • Apapọ ifowosowopo ati awọn ọna orisun akoonu
    • Nlo data kankan rara
    • Ṣe iṣeduro awọn nkan tuntun nikan
  7. What is one limitation of collaborative filtering for a new item with no interactions?
    • It cannot use ratings
    • It requires item descriptions only
    • It may lack the interaction data needed to recommend the item
    • It always recommends every new item
  8. What should a recommender evaluation measure besides click-through rate?
    • Only the model’s parameter count
    • Only training loss
    • Only the number of recommendations
    • User outcomes and harms such as diversity, exposure, or unwanted engagement