期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：5
页码：6670-6675
出版社：TechScience Publications
摘要：The previous work is carried out on sliding window approach for fragment mining rules which results in large & complex processing the data. In this paper we present an idea to find out association within inter-transaction with different windowing approach. These approaches first minimizes the huge input dataset using tumbling window approach and then apply fragment mining to generate rules among different transactions with window length. This experimental work find out effect of different windowing approaches and select the best windowing method which will best suited for processing huge amount of data with minimum complexity . We conclude that this approach is promising one and will be suitable for predictions and useful in stock trading platforms for proper investment in Indian Stock market depend on finance sector.
