Advanced approach for mining utility occupancy patterns in incremental environment

In recent years, one of the varied fields of mining techniques that can discover valuable patterns from databases with vast amounts of data, utility pattern mining, has been studied. Besides, pattern mining techniques considering utility occupancy have been developed, considering the profit, quantity, and proportion of the pattern in transactions. However, recent pattern mining studies for utility occupancy still suffer from obtaining patterns in an incremental environment. Meanwhile, with the widespread adoption of technologies such as IoT or networks, data is rapidly generated and accumulated between devices in real time. Therefore, we suggest IUOIL (Incremental high-Utility Occupancy pattern mining with Indexed List) that discovers patterns having high utility occupancy employing an indexed list-based data structure from databases in an incremental environment. Our algorithm can obtain results by quickening the combination process for patterns using the data structure and reducing search space with three efficient pruning strategies. Performance evaluation is performed using various datasets for comparison with existing algorithms. The assessment on real datasets demonstrated that the technique extracts exact results with the fastest runtime while minimizing memory consumption. In addition, the evaluations on synthetic datasets showed that the technique discovers result set of patterns efficiently and stably as the volume of a database increases.