Improved invasive weed-lion optimization-based process mining of event logs

Process mining is an approach, which can discover and improve business process through extracting knowledge from event logs created in information system. Normally, process execution data in event is supported by information system and technology. Moreover, organizations perform various business processes for serving their clients. Process mining employs event log to determine control flow, process, information and performance about the resources. The precise prediction helps the manager for handling undesired situations with more control, thus future losses can be controlled. In this research, Improved Invasive Lion Algorithm (IILA) is developed for process mining. Furthermore, bounding approach is utilized for trimming the process dimension. In addition, developed IILA is employed for executing process mining. Accordingly, the developed IILA is newly designed by integrating Improved Invasive Weed Optimization (IIWO), and the Lion Algorithm (LA). The fitness measures, like precision and replayability score are also considered for obtaining better process mining performance. However, the performance of developed IILA is evaluated with two metrics, namely replayability and precision. Hence, the developed process mining model outperformed than other existing methods with replayability and precision of 94.44% and 75 respectively.