Search

Research has shown that aggregation of independent expert judgments significantly improves the quality of forecasts as compared to individual expert forecasts. This “wisdom of crowds” (WOC) has sparked substantial interest. However, previous studies on strengths and weaknesses of aggregation algorithms have been restricted by limited empirical data and analytical complexity. Based on a comprehensive analysis of existing knowledge on WOC and aggregation algorithms, this paper describes the design and implementation of a static stochastic simulation model to emulate WOC scenarios with a wide range of parameters. The model has been thoroughly evaluated: the assumptions are validated against propositions derived from literature, and the model has a computational representation. The applicability of the model is demonstrated by investigating aggregation algorithm behavior on a detailed level, by assessing aggregation algorithm performance, and by exploring previously undiscovered suppositions on WOC. The simulation model helps expand the understanding of WOC, where previous research was restricted. Additionally, it gives directions for developing aggregation algorithms and contributes to a general understanding of the WOC phenomenon.

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.

Deciding which business processes to improve is a challenge for all organizations. The literature on business process management (BPM) offers several approaches that support process prioritization. As many approaches share the individual process as unit of analysis, they determine the processes’ need for improvement mostly based on performance indicators, but neglect how processes are interconnected. So far, the interconnections of processes are only captured for descriptive purposes in process model repositories or business process architectures (BPAs). Prioritizing processes without catering for their interconnectedness, however, biases prioritization decisions and causes a misallocation of corporate funds. What is missing are process prioritization approaches that consider the processes’ individual need for improvement and their interconnectedness. To address this research problem, the authors propose the ProcessPageRank (PPR) as their main contribution. The PPR prioritizes processes of a given BPA by ranking them according to their network-adjusted need for improvement. The PPR builds on knowledge from process performance management, BPAs, and network analysis – particularly the Google PageRank. As for evaluation, the authors validated the PPR’s design specification against empirically validated and theory-backed design propositions. They also instantiated the PPR’s design specification as a software prototype and applied the prototype to a real-world BPA.

Cognitive Computing promises to fundamentally transform corporate information processing and problem solving. Building on latest advances in cognitive, data, and computer science, Cognitive Computing aims to deliver autonomous reasoning and continuous learning under consideration of contextual insights and the natural interaction of humans and machines. Cognitive Computing is expected to offer significant application opportunities for business process management (BPM). While first studies have investigated the potential impact of Cognitive Computing on BPM, the intersection between both disciplines remains largely unexplored. In particular, little work has been done on identifying Cognitive BPM use cases. To address this gap, we develop an analysis framework that aims to assist researchers and practitioners in the development of Cognitive BPM use case ideas. This framework combines the most significant problem classes addressed by Cognitive Computing with central activities of the BPM lifecycle. We also used the framework as foundation of explorative workshops and report on the most interesting cognitive BPM use cases ideas we discovered.