Software applications, particularly Enterprise Resource Planning (ERP) systems, are crucial to the day-today operations of many industries, where it is essential to maintain these systems effectively and reliably. In response, Artificial Intelligence for Operations Systems (AIOps) has emerged as a dynamic framework, harnessing cutting-edge analytical technologies like machine learning and big data to enhance incident management procedures by detecting, predicting, and resolving issues while pinpointing their root causes. In this paper, we leverage a promising data-driven strategy, dubbed Subgroup Discovery (SD), a data mining method that can automatically mine incident datasets and extract discriminant patterns to identify the root causes. However, current SD solutions have limitations in handling complex target concepts with multiple attributes organized hierarchically. We illustrate this scenario by examining the case of Java out-of-memory incidents among several possible applications. We have a dataset that describes these incidents, including their topology and the types of Java objects occupying memory when it reaches saturation, with these types arranged hierarchically. This scenario inspires us to propose a novel Subgroup Discovery approach that can handle complex target concepts with hierarchies. To achieve this, we design a new Subgroup Discovery framework along with a pattern syntax and a quality measure that ensure the identified subgroups are relevant, non-redundant, and resilient to noise. To achieve the desired quality measure, we use the Subjective Interestingness model that incorporates prior knowledge about the data and promotes patterns that are both informative and surprising relative to that knowledge. We apply this framework to investigate out-of-memory errors and demonstrate its usefulness in root-cause diagnosis. Notably, this paper stands out as a contribution to both Data Mining and Java memory analysis research. To validate the effectiveness of our approach and the quality of the retrieved patterns, we present an empirical study conducted on a real-world scenario from our ERP system.