Association Rules DATA-SCIENCE-FOUNDATIONS Practice Questions (Page 1)

Questions 1–5

1. 1application · medium

   A data analyst is using the Apriori algorithm and has generated a frequent itemset {A, B, C}. They want to generate all possible association rules from this itemset. How many rules can be generated from this itemset (excluding rules with empty antecedents or consequents)?

   • A12
   • B8
   • C6
   • D3
   Reveal Solution Discussion Select an answer first
2. 2expert · hard

   A data science team is running the Apriori algorithm on a large e-commerce dataset. They are concerned about the number of rules generated and want to focus on actionable insights. They have set a minimum support of 0.01 and a minimum confidence of 0.7. After running the algorithm, they still get thousands of rules. What is the most effective way to reduce the number of rules while keeping the most meaningful ones?

   • AIncrease the minimum lift threshold to filter out rules that do not show a strong association beyond chance.
   • BDecrease the minimum support threshold to allow more itemsets to be considered.
   • CIncrease the minimum confidence threshold to 0.9 to ensure only highly reliable rules are kept.
   • DUse a smaller transaction database to reduce the number of possible itemsets.
   Reveal Solution Discussion Select an answer first
4. 3foundation · easy

   For the rule {milk} → {cereal}, support({milk, cereal}) = 0.2, support({milk}) = 0.4, and support({cereal}) = 0.25. What is the lift of this rule?

   • A2.0
   • B1.25
   • C0.8
   • D0.5
   Reveal Solution Discussion Select an answer first
5. 4application · medium

   A data analyst is comparing two association rules for a marketing campaign. Rule 1: {A} → {B} has support 0.05, confidence 0.8, lift 1.2. Rule 2: {C} → {D} has support 0.01, confidence 0.9, lift 3.0. Which rule is more suitable for a targeted promotion?

   • ARule 1, because higher confidence means the rule is more reliable.
   • BBoth rules are equally suitable because they have similar confidence.
   • CRule 2, because the higher lift indicates a stronger association, making it more effective for targeting.
   • DRule 1, because higher support means the rule applies to more transactions.
   Reveal Solution Discussion Select an answer first
6. 5foundation · easy

   What is the key property exploited by the Apriori algorithm to reduce the number of candidate itemsets considered?

   • AThe monotonicity of confidence: if a rule has high confidence, all its sub-rules also have high confidence
   • BThe upward closure property: if an itemset is frequent, all its supersets are also frequent
   • CThe downward closure property: if an itemset is frequent, all its subsets are also frequent
   • DThe independence assumption: items in a transaction are independent of each other
   Reveal Solution Discussion Select an answer first