Predictive process monitoring aims at forecasting the behavior, performance, and outcomes of business processes at runtime. It helps identify problems before they occur and re-allocate resources before they are wasted. Although deep learning (DL) has yielded breakthroughs, most existing approaches build on classical machine learning (ML) techniques, particularly when it comes to outcome-oriented predictive process monitoring. This circumstance reflects a lack of understanding about which event log properties facilitate the use of DL techniques. To address this gap, the authors compared the performance of DL (i.e., simple feedforward deep neural networks and long short term memory networks) and ML techniques (i.e., random forests and support vector machines) based on five publicly available event logs. It could be observed that DL generally outperforms classical ML techniques. Moreover, three specific propositions could be inferred from further observations: First, the outperformance of DL techniques is particularly strong for logs with a high variant-to-instance ratio (i.e., many non-standard cases).Second, DL techniques perform more stably in case of imbalanced target variables, especially for logs with a high event-to-activity ratio (i.e., many loops in the control flow). Third, logs with a high activity-to-instance payload ratio (i.e., input data is predominantly generated at runtime) call for the application of long short term memory networks. Due to the purposive sampling of event logs and techniques, these findings also hold for logs outside this study.

Process mining, as any form of data analysis, relies heavily on the quality of input data to generate accurate and reliable results. A fit-for-purpose event log nearly always requires time-consuming, manual pre-processing to extract events from source data, with data quality dependent on the analyst's domain knowledge and skills. Despite much being written about data quality in general, a generalisable framework for analysing event data quality issues when extracting logs for process mining remains unrealised. Following the DSR paradigm, we present RDB2Log, a quality-aware, semi-automated approach for extracting event logs from relational data. We validated RDB2Log's design against design objectives extracted from literature and competing artifacts, evaluated its design and performance with process mining experts, implemented a prototype with a defined set of quality metrics, and applied it in laboratory settings and in a real-world case study. The evaluation shows that RDB2Log is understandable, of relevance in current research, and supports process mining in practice.

No abstract

No abstract