What is support and confidence in data mining?

Support and confidence are two important measures in the context of association rule mining, which is a technique used in data mining to discover interesting relationships or patterns in large datasets. These measures help evaluate the strength and significance of the discovered associations between different items in a dataset.

1. Support:

   • Support measures the frequency or the percentage of transactions in a dataset that contain a particular set of items. It indicates how popular or common an itemset is in the dataset.
   • Mathematically, support is calculated as the number of transactions containing the itemset divided by the total number of transactions in the dataset.
   • High support values suggest that the itemset is widely present in the dataset, making it a potentially important pattern.

   Formula: Support(X)=Transactions containing XTotal number of transactionsSupport(X)=Total number of transactionsTransactions containing X

2. Confidence:

   • Confidence measures the reliability or strength of the association rule. It is the conditional probability that a transaction containing one set of items also contains another set of items.
   • Confidence is calculated as the number of transactions containing both the antecedent and consequent divided by the number of transactions containing the antecedent.
   • A high confidence value indicates a strong association between the antecedent and consequent of a rule.

   Formula: Confidence(X→Y)=Support(X∪Y)Support(X)Confidence(X→Y)=Support(X)Support(X∪Y)

   • XX is the antecedent (premise) of the rule.
   • YY is the consequent (outcome) of the rule.
   • X∪YX∪Y represents the union of sets XX and YY.

In summary, support helps identify how frequently an itemset occurs in the dataset, while confidence measures the reliability of the association rule between different itemsets. These metrics are crucial for selecting meaningful and interesting patterns from large datasets in data mining applications.