An efficient approach for incremental erasable utility pattern mining from non-binary data

There are many real-life data incrementally generated around the world. One of the recent interesting issues is the efficient processing real-world data that is continuously accumulated. Mining and recognizing removable patterns in such data is a challenging task. Erasable pattern mining confronts this challenge by discovering removable patterns with low gain. In various real-world applications, data are stored in the form of non-binary databases. These databases store item information in a quantity form. Since items in the database can each have different characteristics, such as quantities, considering their relative features makes the mined patterns more meaningful. For these reasons, we propose an erasable utility pattern mining algorithm for incremental non-binary databases. The suggested technique can recognize removable patterns by considering the relative utility of items and the profit of products in an incremental database. The proposed algorithm utilizes a list structure for efficiently extracting erasable utility patterns. Several experiments have been conducted to compare the performance between the suggested algorithm and state-of-the-art techniques using real and synthetic datasets, and the results demonstrate the effectiveness of the proposed method.