Distributed pruning optimization oriented FP-Growth method based on PSO algorithm

Chen, Hongwei; Luo, Qixing; Chen, Zexi; Chen, Ying-Zhe

doi:10.1109/itnec.2017.8284975

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FP Growth is kind of an improved version (successor) of the a priori algorithm. It can generate frequent patterns without candidate generation step from a priori algorithm; it refers to generating a tabular representation of combination of items scored with its count of re-appearing frequency [1,4]. FP Growth algorithm can visually represent the database in a tree structure which is easy to understand and is referred as FP Tree OR Frequent Pattern Tree.…”

Section: Fp Growthmentioning

confidence: 99%

Customer Behavioral Market Basket Approach for Most Frequent Pattern Identification Using Data Mining Techniques

Joshi¹,

Rathod²,

Parekh

et al. 2021

ICT With Intelligent Applications

View full text Add to dashboard Cite

Advertise bushel investigation analyzes customers' purchasing patterns by finding unexpected and important associations among the products which they place in their shopping baskets. It not only assists in decision-making process but also increases sales in many business organizations. A priori and FP Growth are the most common algorithms for mining frequent itemsets. For both algorithms a predefined minimum support is needed to satisfy for identifying the frequent itemset. But when the minimum support is low, a huge statistical change of count in candidate sets will be generated that needs large computation. In this paper, an approach has been proposed to avoid this large computation by reducing the items of dataset with top selling products. Various percentages of trending products like 30 to 55% are selected and for both FP growth and a priori algorithm, association rule generation process starts along with frequent item combinations. The comes about appear that in case beat offering things are utilized, it is conceivable to urge nearly same visit itemset and affiliation rules inside a brief time comparing with that yields which are derived by computing all the things. From time comparison, it is also found that Distributed FP Development calculation takes littler time than a priori calculation.

show abstract

Section: Fp Growthmentioning

confidence: 99%