Test
Association KHT - Machine Learning
Preguntas del test (5)
1What are the two pillars in which Association Analysis is based?
- AAntecedents and Consequents
- BFrequency and rule reliability
- CPrior and Posterior Confidence
- DItem sets and Rule support
2Which of these statements regarding Association is FALSE?
- AFor customer level predictions, Tabular format is preferred
- BConfidence Ratio range is (-1 , 1)
- CTransactional format usually generates more records
- DLift can be lower than 1
3Based on the image and rule given, what are Support and Confidence values?

- AS: 80%, C: 20%
- BNone of the others
- CS: 40%, C: 80%
- DS: 20%, C: 40%
4If Confidence Difference threshold for a rule is 60, which one of the following is FALSE?
- AThere will be no positive rules for products with Prior Confidences > 40
- BNegatives rules cannot be extracted
- CRules with low Confidence values may be extracted
- DWith only this information there is no way to calculate Lift
5Based on the image below, which of the following statements is CORRECT?

- AAntecedents + Consequent are present in approx. 0.6% of tickets
- BConf. ratio is approximately 0.4
- CLift is approx. 0.6
- DConfidence difference is absolute value of (0.40 - 0.006)
Información
- Descripción
- Informática Test sobre Association KHT - Machine Learning, creado por Angel Intriago el 12/12/2021.
- Autor
- Angel Intriago
- Idioma
- English
- Visitas
- 7
- Etiquetas
- Valoración
- Aún sin valoraciones Valora este test