Association rule mining is finding associations or patterns among a collection of items which occur frequently. It is also known as Market basket analysis.
Its main aim is to understand the buying habits of the customer, which is done by finding the correlations and patterns among the items that customers intended to buy or actually bought. For example, a customer who buys a computer keyboard is also likely to buy a computer mouse or a pen drive.
The rule is given by:
Antecedent → Consequent [support, confidence]
Let A, B, C, D, and E .... represent different items.
Then we need to generate association rules, for example:
{A, J} → {C}
{M, D, J} → {X}
The first rule here means that when A and J are bought together then there is a high probability of the customer buying C too.
Similarly, the second rule means that when M, D, and J are bought together there is a high probability of the customer buying X too.
These rules are measured by:
Support...