scholarly journals A novel collaborative filtering algorithm by bit mining frequent itemsets

2018 ◽  
Author(s):  
Loc Nguyen ◽  
Minh-Phung T. Do
Keyword(s):  
Collaborative Filtering ◽  
Frequent Itemsets ◽  
Frequent Itemset ◽  
Storage Space ◽  
Model Based ◽  
Collaborative Filtering Algorithm ◽  
Speed Up ◽  
Mining Frequent Itemsets ◽  
Bitwise Operations ◽  
Process Mode

Collaborative filtering (CF) is a popular technique in recommendation study. Concretely, items which are recommended to user are determined by surveying her/his communities. There are two main CF approaches, which are memory-based and model-based. I propose a new CF model-based algorithm by mining frequent itemsets from rating database. Hence items which belong to frequent itemsets are recommended to user. My CF algorithm gives immediate response because the mining task is performed at offline process-mode. I also propose another so-called Roller algorithm for improving the process of mining frequent itemsets. Roller algorithm is implemented by heuristic assumption “The larger the support of an item is, the higher it’s likely that this item will occur in some frequent itemset”. It models upon doing white-wash task, which rolls a roller on a wall in such a way that is capable of picking frequent itemsets. Moreover I provide enhanced techniques such as bit representation, bit matching and bit mining in order to speed up recommendation process. These techniques take advantages of bitwise operations (AND, NOT) so as to reduce storage space and make algorithms run faster.

scholarly journals A novel collaborative filtering algorithm by bit mining frequent itemsets

2018 ◽  
Author(s):  
Loc Nguyen ◽  
Minh-Phung T. Do
Keyword(s):  
Collaborative Filtering ◽  
Frequent Itemsets ◽  
Frequent Itemset ◽  
Storage Space ◽  
Model Based ◽  
Collaborative Filtering Algorithm ◽  
Speed Up ◽  
Mining Frequent Itemsets ◽  
Bitwise Operations ◽  
Process Mode

Collaborative filtering (CF) is a popular technique in recommendation study. Concretely, items which are recommended to user are determined by surveying her/his communities. There are two main CF approaches, which are memory-based and model-based. I propose a new CF model-based algorithm by mining frequent itemsets from rating database. Hence items which belong to frequent itemsets are recommended to user. My CF algorithm gives immediate response because the mining task is performed at offline process-mode. I also propose another so-called Roller algorithm for improving the process of mining frequent itemsets. Roller algorithm is implemented by heuristic assumption “The larger the support of an item is, the higher it’s likely that this item will occur in some frequent itemset”. It models upon doing white-wash task, which rolls a roller on a wall in such a way that is capable of picking frequent itemsets. Moreover I provide enhanced techniques such as bit representation, bit matching and bit mining in order to speed up recommendation process. These techniques take advantages of bitwise operations (AND, NOT) so as to reduce storage space and make algorithms run faster.

scholarly journals Implementation of Improved Association Rule Mining Algorithms for Fast Mining with Efficient Tree Structures on Large Datasets

2019 ◽  
Vol 9 (2) ◽  
pp. 5136-5141
Keyword(s):  
Association Rule ◽  
Frequent Itemsets ◽  
Large Datasets ◽  
Frequent Itemset ◽  
Rule Mining ◽  
Tree Structures ◽  
Significant Area ◽  
Dataset Size ◽  
Mining Algorithms ◽  
Mining Frequent Itemsets

ARM is a significant area of knowledge mining which enables association rules which are essential for decision making. Frequent itemset mining has a challenge against large datasets. As going on the dataset size increases the burden and time to discover rules will increase. In this paper the ARM algorithms with tree structures like FP-tree, FIN with POC tree and PPC tree are discussed for reducing overheads and time consuming. These algorithms use highly competent data structures for mining frequent itemsets from the database. FIN uses nodeset a unique and novel data structure to extract frequent itemsets and POC tree to store frequent itemset information. These techniques are extremely helpful in the marketing fields. The proposed and implemented techniques reveal that they have improved about performance by means of time and efficiency

scholarly journals An enhanced constraint based technique for frequent itemset mining in transactional databases

2018 ◽  
Vol 7 (2.22) ◽  
pp. 45
Author(s):  
Ramah Sivakumar ◽  
Dr J.G.R. Sathiaseelan
Keyword(s):  
Processing Time ◽  
Frequent Itemsets ◽  
Frequent Itemset ◽  
Frequent Patterns ◽  
Unique Minimum ◽  
Itemset Mining ◽  
Transactional Databases ◽  
Pros And Cons ◽  
Social Applications ◽  
Mining Frequent Itemsets

Mining frequent patterns is one of the wide area of research in recent times as it has numerous social applications.  Variety of frequent patterns finds usage in diverse applications and the research to mine those in an optimized way is an important aspect under consideration.  So far, many algorithms had been proposed for mining frequent itemsets and each has their own pros and cons.  The basic algorithms used in the process are Apriori, Fpgrowth and Eclat.  Many enhancements of these algorithms are ongoing process in recent times.  In this paper, an enhanced Varied Support Frequent Itemset (VSFIM) algorithm is proposed which is an enhancement of FPGrowth algorithm. Unique minimum support for each item in the transaction is provided and then mining is done in the proposed approach.   The performance of the proposed algorithm is tested with existing algorithms.  It is found that VSFIM outperformed the existing algorithms in both processing time and space utilization.  

scholarly journals Mining Frequent Itemsets Over Uncertain Database using Matrix

2020 ◽  
Vol 9 (4) ◽  
pp. 2048-2052
Keyword(s):  
Data Mining ◽  
Frequent Itemsets ◽  
Frequent Itemset ◽  
Apriori Algorithm ◽  
Computation Complexity ◽  
Support Count ◽  
Frequent Items ◽  
Uncertain Database ◽  
Modern Era ◽  
Mining Frequent Itemsets

In the area of data mining for finding frequent itemset from huge database, there exist a lot of algorithms, out of all Apriori algorithm is the base of all algorithms. In Uapriori algorithm each items existential probability is examined with a given support count, if it is greater or equal then these items are known as frequent items, otherwise these are known as infrequent itemsets. In this paper matrix technology has been introduced over Uapriori algorithm which reduces execution time and computational complexity for finding frequent itemset from uncertain transactional database. In the modern era, volume of data is increasing exponentially and highly optimized algorithm is needed for processing such a large amount of data in less time. The proposed algorithm can be used in the field of data mining for retrieving frequent itemset from a large volume of database by taking very less computation complexity.

The Optimization Algorithm of Association Rules Mining

2014 ◽  
Vol 614 ◽  
pp. 405-408
Author(s):  
Zhen Yu Liu ◽  
Zhi Hui Song ◽  
Rui Qing Yan ◽  
Zeng Zhang
Keyword(s):  
Association Rules ◽  
Frequent Itemsets ◽  
Decision Makers ◽  
Generation Process ◽  
Association Rules Mining ◽  
Rule Sets ◽  
Speed Up ◽  
Frequent Itemsets Mining ◽  
Encoding Method ◽  
Mining Frequent Itemsets

Frequent itemsets mining is the core part of association rule mining. At present most of the research on association rules mining is focused on how to improve the efficiency of mining frequent itemsets , however, the rule sets generated from frequent itemsets are the final results presented to decision makers for making, so how to optimize the rulesets generation process and the final rules is also worthy of attention. Based on encoding the dataset, this paper proposes a encoding method to speed up the generation process of frequent itemsets and proposes a subset tree to generate association rules which can simplify the generation process of rules and narrow the rulesets presented to decision makers.

The Research of Cloud Platform Based on KNN Collaborative Filtering Algorithm in Fruits Marketing System

2013 ◽  
Vol 373-375 ◽  
pp. 1826-1829
Author(s):  
Li Luo ◽  
Xiao Ling Gao ◽  
De Jun Wu
Keyword(s):  
Collaborative Filtering ◽  
High Speed ◽  
Large Scale ◽  
Recommendation System ◽  
Marketing System ◽  
Filtering Algorithm ◽  
Computing Platform ◽  
Large Scale Data ◽  
Collaborative Filtering Algorithm ◽  
Speed Up

With the development of internet, we usually hope to recommender the possible interested products to the consumers through analyzing to the consumers history records, and obtain better sale records in fruits marketing system. collaborative filtering algorithm is widely used in Fruits Recommendation System, and item-based KNN collaborative filtering algorithm completes clustering and recommendation through analyzing the similarity of the items. Traditional item-based KNN collaborative filtering algorithm could not deal with huge scale fruits sale data effectively to complete recommendation work. In this paper, for the large scale data, we propose a distributed item-based KNN collaborative filtering algorithm based on MapReduce cloud computing platform. The experimental results show that the algorithm has a high speed-up, and a good expansibility.

scholarly journals NUCLEAR: An Efficient Methods for Mining Frequent Itemsets and Generators from Closed Frequent Itemsets

2021 ◽  
Vol 7 (2) ◽  
Author(s):  
Huy Quang Pham, Duc Tran, Ninh Bao Duong, Philippe Fournier-Viger, Alioune Ngom
Keyword(s):  
Data Mining ◽  
Frequent Itemsets ◽  
Frequent Itemset ◽  
Experimental Results ◽  
Extra Cost ◽  
Effective Algorithm ◽  
Closed Frequent Itemsets ◽  
Mining Frequent Itemsets

Frequent itemset (FI) mining is an interesting data mining task. Instead of directly mining the FIs from data it is preferred to mine only the closed frequent itemsets (CFIs) first and then extract the FIs for each CFI. However, some algorithms require the generators for each CFI in order to extract the FIs, leading to an extra cost. In this paper, we introduce an effective algorithm, called NUCLEAR, which can induce the FIs from the lattice of CFIs without the need of the generators. It can enumerate generators as well by similar fashion. Experimental results showed that NUCLEAR is effective as compared to previous studies, especially, the time for extracting the FIs is usually much smaller than that for mining the CFIs.

Sign in / Sign up

Export Citation Format

Share Document