Comparative Analysis of Frequent Pattern Mining Algorithms

Abstract Frequent Pattern Mining (FPM) is a fundamental data mining task that identifies associations and patterns within datasets. We explore different techniques by reviewing prominent algorithms like Apriori, EClaT, FP-Growth, FIN, PrePost+, Pascal and LCMFreq. We categorize these approaches based on their candidate generation, data representation, and computational strategies, ranging from tree-based methods to pattern growth techniques. Numerical simulations are conducted on real-world datasets to compare their performance in terms of runtime, memory consumption, and scalability across different support thresholds.