SPADE (Sequential Pattern Discovery Using Equivalence classes) discovers frequent event sequences by analyzing ordered transactions. It extends transaction-based pattern mining to reveal what occurs next, supporting applications such as customer behavior, online searches, DNA sequencing, marketing, and user interaction analysis. section 4.7 section 4.7.1
An item is an element of the item universe; an event is a collection of items in one transaction; and a sequence orders events, such as (Milk, Cheese) -> (Bread, Eggs). A k-item sequence contains k items across its events. section 4.7.1
Python execution
A Python implementation can read a prepared sequence file, mine patterns with a support threshold of 0.6, and print the results: spade_result = spade(filename='SPADE_dataset.txt', support=0.6, parse=True); print_result(spade_result).
