Modified Improved Apriori Algorithm for Reduced Time Complexity

• Published in: 2025 4th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0 pp. 1 - 5
• Main Authors: Tiwari, Geeta, Dubey, Shirish Mohan, Sharma, Gaurav, Bansal, Apporva
• Format: Conference Proceeding
• Language: English
• Published: IEEE 09.04.2025
• Subjects: Approximation algorithms; Enhanced Apriori Algorithm; Frequent item Introduction; Frequent Pattern Mining; Itemsets; Machine learning; Machine learning algorithms; Multicore processing; Parallel Computing; Parallel processing; Program processors; Runtime; Technological innovation; Time complexity; Transactional Dataset
• DOI: 10.1109/OTCON65728.2025.11070961

In today's era, transactional datasets are ubiquitous and continue to grow in size, making it increasingly challenging to mine frequent itemsets efficiently. The Apriori algorithm is a well-known method for mining frequent itemsets, but it suffers from high time complexity as the size of the dataset increases. In this paper, we propose a multicore modified Apriori algorithm using machine learning to address this challenge. Our proposed algorithm leverages the parallel processing capability of modern multicore processors and integrates machine learning techniques to reduce the time complexity of the Apriori algorithm. The results of our experiments show that our proposed algorithm significantly outperforms other Apriori algorithms in terms of runtime, making it a promising solution for mining frequent itemsets from large transactional datasets.