Abstract Association Rule Mining Research Articles

Comparative Analysis of Association Rule Mining Algorithms in Market Basket Analysis Using Transactional Data

Association rule mining (ARM) is an aspect of data mining that has revolutionized the area of predictive modelling paving way for data mining technique to become the recommended method for business owners to evaluate organizational performance. Market basket analysis (MBA), a useful modeling technique in data mining, is often used to analyze customer buying pattern. Choosing the right ARM algorithm to use in MBA is somewhat difficult, as most algorithms performance is determined by characteristics such as amount of data used, application domain, time variation, and customer’s preferences. Hence this study examines four ARM algorithm used in MBA systems for improved business Decisions. One million, one hundered and twele thousand (1,112,000) transactional data were extracted from Babcock University Superstore. The dataset was induced with Frequent Pattern Growth, Apiori, Association Outliers and Supervised Association Rule ARM algorithms. The outputs were compared using minimum support threshold, confidence level and execution time as metrics. The result showed that The FP Growth has minimum support threshold of 0.011 and confidence level of 0.013, Apriori 0.019 and 0.022, Association outliers 0.026 and 0.294 while Supervised Association Rule has 0.032 and 0.212 respectively. The FP Growth and Apirori ARM algorithms performed better than Association Outliers and Supervised Association Rule when the minimum support and confidence threshold were both set to 0.1. The study concluded by recommending a hybrid ARM algorithm to be used for building MBA Applications. The outcome of this study when adopted by business ventures will lead to improved business decisions thereby helping to achieve customer retention.
 Keywords: Association rule mining, Business ventures, Data mining, Market basket analysis, Transactional data.

An Improved Group Similarity-Based Association Rule Mining Algorithm in Complex Scenes

Association rule (AR) mining in complex scene has attracted extensive attention of researchers in recent years. Typically, many researchers focused on an algorithm itself and ignored a generalization method to improve the performance of AR mining. Tuna et al., presented a general data structure Speeding-Up AR Structure with Inverted Index Compression (SAII) which could be utilized in most of the existing algorithms to improve their performance IEEE Trans. Cybern. 46(12) (2016) 3059–3072. However, we found that this algorithm consumes a lot of time in re-ordering data because a one-to-one comparison method is used in this process, which is the main reason that the speeding-up structure is difficult to establish when coping with much more large amount of data. To overcome these problems, this paper aims to propose an improved speeding-up AR algorithm based on group similarity and Apache Spark framework to further reduce the memory requirements and runtime. Our simulation results on the police business big dataset make clear that our improved approach performs well and is more suitable for a big data environment.

Association rule mining with a correlation-based interestingness measure for video semantic concept detection

Association rule mining (ARM) has been adopted in automatic semantic concept detection to discover the association patterns from the multimedia data and predict the target concept classes. As a rule-based method, ARM faces the challenges on rule pruning. Such challenges could be addressed by utilising proper interestingness measures. In this paper, a video semantic concept detection framework that uses ARM together with a novel correlation-based interestingness measure is proposed. The interestingness measure is obtained from applying multiple correspondence analysis (MCA) to capture the correlation between features and concept classes. This new correlation-based interestingness measure is first used in the rule generation stage, and then reused and combined with the inter-similarity and intra-similarity values to select the final rule set for classification. Experimented with 14 concepts from the benchmark TRECVID data, our proposed framework achieves higher accuracy than the other six classifiers that a...

The importance of negative associations and the discovery of association rule pairs

Association Rule Mining (ARM) technique is one of the popular data mining techniques used to discover knowledge from a database. In this paper, we highlight the subsequent drawbacks to association rule mining without considering the absence of items. We propose a novel approach to mine both positive and negative association rules as rule pairs. Our approach ensures that impacts of negative associations are considered so that the drawbacks identified can be avoided. Our initial experiment results show that mining pairs of association rules invoking negative associations are small in number and easy to be appreciated for its implications for decision-making.