Analyzing Resource Behavior Using Process Mining

Abstract

Abstract. It is vital to use accurate models for the analysis, design, and/or control of business processes. Unfortunately, there are often important discrepancies between reality and models. In earlier work, we have shown that simulation models are often based on incorrect assumptions and one example is the speed at which people work. The "Yerkes-Dodson Law of Arousal" suggests that a worker that is under time pressure may become more efficient and thus finish tasks faster. However, if the pressure is too high, then the worker's performance may degrade. Traditionally, it was difficult to investigate such phenomena and few analysis tools (e.g., simulation packages) support workload-dependent behavior. Fortunately, more and more activities are being recorded and modern process mining techniques provide detailed insights in the way that people really work. This paper uses a new process mining plug-in that has been added to ProM to explore the effect of workload on service times. Based on historic data and by using regression analysis, the relationship between workload and services time is investigated. This information can be used for various types of analysis and decision making, including more realistic forms of simulation.

Generating Event Logs with Workload-Dependent Speeds from Simulation Models

“…The start date of the log is "18-11-2009" and the end date is "12-01-2012". The results reported in this section are based on an extended implementation of a ProM plug-in described in [11] which quantifies the relationship between workload (using the queue length and how busy notions) and processing speeds (denoted by service and waiting times of events). Here, we use regression analysis to quantify the effect of workload (as the independent variable x),i.e., denoted based on queue length and how busy perspectives and processing speed (as the dependent variable y), i.e., denoted as service times of activities.…”

“…The results discussed in this section follow the first half of the Yerkes-Dodson law. Given that the simulation model generates event logs, it is now possible to analyse those logs using the process mining techniques that we have described in this section and in our earlier work [11]. Although varying workload has an effect on the speed at which resources work, when building simulation models this is rarely taken into account.…”

“…2. If the law holds, the performance of people (i.e., the speed at which they work) is determined by the workload that is currently present in the system [5,11,13]. This implies that for a given individual and a given set of tasks, there is an optimal level at which the performance of that individual has a maximal value and beyond this optimal level, the worker's performance collapses.…”

Beyond Process Mining: From the Past to Present and Future

“…People do not work at constant speeds and need to distribute their attention over multiple processes. This can have dramatic effects on the performance of a process [2,15] and, therefore, such aspects should not be "abstracted away". Second, various artifacts available are not used as input for simulation.…”

“…In [15] it is shown how event logs can be used to learn about the behavior of people. For example, through process mining one can find empirical evidence for the Yerkes-Dodson law [23] and parameterize the corresponding simulation models.…”