Ikibazo gihuza ibibazo · Hagati Urwego

A / B Ikizamini cya ML Model Ikibazo

Reba urufatiro rwubushakashatsi bwikitegererezo kumurongo, harimo umukoro uteganijwe, ibizamini bya hypothesis, kugabana imiterere, hamwe nuburinzi.

Inzira zijyanye no kuyoboraA B Ikizamini cya ML Model
Ikibazo 1 Bya 8

Kuki amakipe A / B yerekana ikigereranyo mubikorwa aho kwizera ibipimo bya interineti?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Kuki amakipe A / B yerekana ikigereranyo mubikorwa aho kwizera ibipimo bya interineti?
    • Icyitegererezo gifite neza neza kuri interineti kirashobora kubabaza ibipimo byubucuruzi nyabyo
    • Ibipimo bya interineti bitemewe
    • Umusaruro uhendutse kuruta kugerageza kumurongo
    • Amakuru ya Offline ntabwo abaho
  2. Ni uruhe ruhare umukoro uteganijwe ugira mu kizamini cya A / B.
    • Bituma ikizamini gikora vuba
    • It supports balance between groups in expectation, subject to design and implementation assumptions
    • Isiba abakoresha babogamye
    • Igabanya umubare wicyitegererezo gikenewe
  3. In a model A/B test, what usually happens in the treatment group?
    • The candidate scores requests but all outputs are withheld
    • Every user is assigned to both models for the same decision
    • The candidate model serves user-facing decisions for the randomly assigned group
    • The control model is removed before any comparison
  4. Under a null hypothesis and stated test assumptions, how is a p-value interpreted?
    • As the probability that the null hypothesis is true
    • As the probability that the treatment caused the observed result
    • As the probability that the experiment will replicate
    • As the probability of data at least this extreme if the null hypothesis holds
  5. Nigute amabandi afite intwaro nyinshi ashobora guhindura igerageza mugihe ikora?
    • It can allocate more traffic to variants with better observed outcomes and less to others
    • It keeps every variant at a fixed equal allocation throughout
    • It removes randomization from every assignment
    • It guarantees the best variant is identified without uncertainty
  6. Niyihe ntego yo gusesengura imbaraga mbere yikizamini cya A / B.
    • Guhitamo ikirango cyo kugerageza
    • Kugereranya umubare wabakoresha bakeneye kugirango bamenye neza ingaruka nyazo
    • Kugenzura ibinyabiziga
    • Gusiba itsinda rishinzwe kugenzura
  7. What does a sample-ratio mismatch (SRM) signal during an A/B test?
    • The treatment model is necessarily better
    • The experiment has sufficient statistical power
    • Observed assignment counts differ materially from the configured allocation, which can indicate a data or randomization problem
    • The primary metric improved causally
  8. Why include guardrail metrics alongside an experiment’s primary success metric?
    • To guarantee the candidate wins on every metric
    • To replace the primary metric after results are observed
    • To avoid defining a decision rule before the test
    • To detect meaningful harms in other outcomes even when the primary metric improves