1. Introduction
Process Mining aims to extract information from event logs to highlight the underlying business processes. This relatively recent discipline, halfway between Business Process Management and Data Mining, mainly focuses on constructing processes based on data recorded in Information Systems. Several techniques have been proposed so far, tackling the main challenges raised by todays' Information Systems, such as noise or incompleteness. But rather few of them take into account implicit dependencies. Most the time, this phenomenon, where the execution of an activity depends on the execution of another activity, is not clearly expressed by the process models built by the different Process Mining techniques. But it has as effect to restrain the model behavior. As the algorithms or the graphical representations used so far to tackle such implicit dependencies are not suitable in the context of our work, we introduce the Implicit Dependencies Miner, a Process Tree based algorithm we developed in order to detect the relevant dependencies that might exist between activities. This paper is organized as follows. In section 2, we present the Process Mining and the related work. In section 3, we define the context of our approach. In section 4, we introduce the Implicit Dependencies Miner (IDM). In section 5, we apply the IDM on an artificial log. Finally, in section 6 we present a conclusion and the future work.