In data mining, Apriori is a classic algorithm for learning association rules. Apriori is designed to work on databases that contain transactions (for example, collections of items purchased by customers, or details of a website frequenting).
Other algorithms are designed to find association rules in data that have no transactions (Winepi and Minepi), or that have no time stamps (DNA sequencing).
The whole point of the algorithm (and data mining, in general) is to extract useful information from large amounts of data. For example, information that a customer buying a keyboard also tends to buy a mouse at the same time is acquired from the association rule below:
Support: The percentage of data-relevant data transactions for which the pattern is true.
Support (Keyboard -> Mouse) =
![[Image: eq_1.JPG]](https://www.codeproject.com/KB/recipes/AprioriAlgorithm/eq_1.JPG)
Trust: The measure of certainty or reliability associated with each pattern discovered.
Trust (Keyboard -> Mouse) =
The algorithm aims to find the rules that satisfy both a minimum support threshold and a minimum trust threshold (Strong Rules).
• Item: item in the basket.
• Set of items: a group of items purchased together in a single transaction.