A Rational Risk Policy? Why Path Dependence Matters.

The Kelly criterion determines optimal bet sizes that maximize long-term growth. While growth is definitely an important consideration, the focus on growth alone can lead to significant drawdowns, leading to psychological discomfort for a risk-taker. Path-dependent risk measures, such as drawdown risk, provide a means to assess the risk of significant portfolio retracements. In this paper, we provide a flexible framework for assessing path dependent risk for a trading or investment operation. Given a certain set of profitable trading characteristics, a risk-taker who maximizes expected growth can still be faced with significant drawdowns to the point where a strategy becomes unsustainable. We demonstrate, through a series of experiments, the importance of path dependent risks in the case of outcomes subject to various return distributions. Based on Monte Carlo simulation, we analyze the medium-term behavior of different cumulative return paths and study the impact of different return outcome distributions. We show that in the case of heavier tailed outcomes, extra care is needed, and optimal might not be so optimal in the end.

Supporting capacity management decisions in healthcare using data-driven process simulation.

Healthcare managers are confronted with various Capacity Management decisions to determine appropriate levels of resources such as equipment and staff. Given the significant impact of these decisions, they should be taken with great care. The increasing amount of process execution data - i.e. event logs - stored in Hospital Information Systems (HIS) can be leveraged using Data-Driven Process Simulation (DDPS), an emerging field of Process Mining, to provide decision-support information to healthcare managers. While existing research on DDPS mainly focuses on the fully automated discovery of simulation models from event logs, the interaction between process execution data and domain expertise has received little attention. Nevertheless, data quality issues in real-life process execution data stored in HIS prevent the discovery of accurate and reliable models from this data. Therefore, complementary information from domain experts is necessary. In this paper, we describe the application of DDPS in healthcare by means of an extensive real-life case study at the radiology department of a Belgium hospital. In addition to formulating our recommendations towards the radiology management, we will elaborate on the experienced challenges and formulate recommendations to move research on DDPS within a healthcare context forward. In this respect, explicit attention is attributed to data quality assessment, as well as the interaction between the use of process execution data and domain expertise.

Mining context-aware resource profiles in the presence of multitasking.

Healthcare organisations are becoming increasingly aware of the need to improve their care processes and to manage their scarce resources efficiently to secure high-quality care standards. As these processes are knowledge-intensive and heavily depend on human resources, a comprehensive understanding of the complex relationship between processes and resources is indispensable for efficient resource management. Organisational mining, a subfield of Process Mining, reveals insights into how (human) resources organise their work based on analysing process execution data recorded in Health Information Systems (HIS). This can be used to, e.g., discover resource profiles which are groups of resources performing similar activity instances, providing an extensive overview of resource behaviour within healthcare organisations. Healthcare managers can employ these insights to allocate their resources efficiently, e.g., by improving the scheduling and staffing of nurses. Existing resource profiling algorithms are limited in their ability to apprehend the complex relationship between processes and resources because they do not take into account the context in which activities were executed, particularly in the context of multitasking. Therefore, this paper introduces ResProMin-MT to discover context-aware resource profiles in the presence of multitasking. In contrast to the state-of-the-art, ResProMin-MT is capable of taking into account more complex contextual activity dimensions, such as activity durations and the degree of multitasking by resources. We demonstrate the feasibility of our method within a real-life healthcare context, validated by medical domain experts.

Traffic accident segmentation by means of latent class clustering.

Traffic accident data are often heterogeneous, which can cause certain relationships to remain hidden. Therefore, traffic accident analysis is often performed on a small subset of traffic accidents or several models are built for various traffic accident types. In this paper, we examine the effectiveness of a clustering technique, i.e. latent class clustering, for identifying homogenous traffic accident types. Firstly, a heterogeneous traffic accident data set is segmented into seven clusters, which are translated into seven traffic accident types. Secondly, injury analysis is performed for each cluster. The results of these cluster-based analyses are compared with the results of a full-data analysis. This shows that applying latent class clustering as a preliminary analysis can reveal hidden relationships and can help the domain expert or traffic safety researcher to segment traffic accidents.

Developing an emergency department crowding dashboard: A design science approach.

BACKGROUND: As an emergency department (ED) is a complex adaptive system, the analysis of continuously gathered data is valuable to gain insight in the real-time patient flow. To support the analysis and management of ED operations, relevant data should be provided in an intuitive way. AIM: Within this context, this paper outlines the development of a dashboard which provides real-time information regarding ED crowding. METHODS: The research project underlying this paper follows the principles of design science research, which involves the development and study of artifacts which aim to solve a generic problem. To determine the crowding indicators that are desired in the dashboard, a modified Delphi study is used. The dashboard is implemented using the open source Shinydashboard package in R. RESULTS: A dashboard is developed containing the desired crowding indicators, together with general patient flow characteristics. It is demonstrated using a dataset of a Flemish ED and fulfills the requirements which are defined a priori. CONCLUSIONS: The developed dashboard provides real-time information on ED crowding. This information enables ED staff to judge whether corrective actions are required in an effort to avoid the adverse effects of ED crowding.