Quiz ngir gis njuuj njaaj ci IA

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan moo waral sàrt yuñ tëral kese (lu melni, 'block charges yu ëpp $5,000') duñu doy ngir njuuj njaaj?
   • Njuuj njaaj dafay xeex te dafay soppeeku saa yu nekk, moo tax sàrt yi dañuy yàgg
   • Dañu seer lool ci bind
   • Bànk yi waru ñu jëfandikoo ay sàrt
   • Yoon yi duñu dox ludul ci njeexte ayu-bis yi
2. 'Déséquilibre ci klaas' ci gis njuuj njaaj mingi aju ci ni:
   • Bànk yi bari nañu lool
   • Jëflante yu baaxul yi lu tuuti la ci jëflante yépp
   • Kiliyaan yépp dañuy dugal benn xaalis
   • Done yi dañu leen denc ci fichier class bu jaarul yoon
3. 'Njuumteg positif' ci gis njuuj njaaj mooy:
   • Dañu namm njuuj njaaj dëgg
   • Sistem bi dafa tass
   • Jëflante bu jaar yoon, dañu ko juum ci wax ni njuuj njaaj la
   • ñaari sarse am
4. What challenge can neighbor-based message propagation create for a fraud GNN?
   • It guarantees every linked account is fraudulent
   • It removes all concept drift from the data
   • It prevents investigators from reviewing transactions
   • Neighbor and hub effects can amplify class-imbalance problems
5. Ban siñaal mooy misaalu 'gaawaay' ci di wottu jëflante?
   • sarse yu bari di am ci ay simili yu néew
   • Aniwerseer kiliyaan bi
   • Kulòoru kàrt bi
   • Logo bànk bi
6. What fraud typology did FinCEN’s 2024 deepfake alert describe?
   • Deepfakes that automatically reverse settled transactions
   • Deepfake media and fraudulent identity documents used to evade identity verification or authentication
   • A rule requiring banks to reject every voice call
   • Synthetic identities that prove a customer committed a crime
7. Why can accuracy be misleading for a highly imbalanced fraud dataset?
   • Accuracy is always equal to recall
   • Fraud labels are never used
   • A model can score high accuracy by predicting the majority legitimate class while missing fraud
   • The test set must contain no legitimate transactions
8. What is one reason a graph model can help identify linked fraud patterns?
   • It removes the need for labels or investigation
   • It proves that connected accounts are criminal
   • It guarantees real-time detection
   • It can represent relationships among accounts, transactions, or devices