Prescriptive Process Monitoring Under Resource Constraints: A Causal Inference Approach

Abstract

Prescriptive process monitoring is a family of techniques to optimize the performance of a business process by triggering interventions at runtime. Existing prescriptive process monitoring techniques assume that the number of interventions that may be triggered is unbounded. In practice, though, specific interventions consume resources with finite capacity. For example, in a loan origination process, an intervention may consist of preparing an alternative loan offer to increase the applicant's chances of taking a loan. This intervention requires a certain amount of time from a credit officer, and thus, it is not possible to trigger this intervention in all cases. This paper proposes a prescriptive process monitoring technique that triggers interventions to optimize a cost function under fixed resource constraints. The proposed technique relies on predictive modeling to identify cases that are likely to lead to a negative outcome, in combination with causal inference to estimate the effect of an intervention on the outcome of the case. These outputs are then used to allocate resources to interventions to maximize a cost function. A preliminary empirical evaluation suggests that the proposed approach produces a higher net gain than a purely predictive (non-causal) baseline.

Prescriptive Process Monitoring: Quo Vadis?

“…For instance, Gröger et al [16] describe the example of a manufacturing process, where the target is to avoid exceeding the allowed limits for cycle time. Another set of studies focuses on avoiding or mitigating an undesired categorical outcome [37,13,27,35,14,39,25,17]. For example, Ghattas et al [14] try to avoid the customer rejecting the delivery in a bottle manufacturing process.…”

“…Some papers propose prescribing multiple interventions for one case [35,30,5]. For example, an intervention to make an offer to a client is prescribed together with a suggestion for a specific clerk to carry out the task [35].…”

“…Some papers propose prescribing multiple interventions for one case [35,30,5]. For example, an intervention to make an offer to a client is prescribed together with a suggestion for a specific clerk to carry out the task [35]. Similarly, in an IT service management process, recommending the next task and the specialist to perform it can help to resolve open cases quicker [30].…”

“…Discrete methods leave it up to the users (stakeholders) to define the possible intervention(s) a priori (e.g., [23,37]). Those methods that use observational event logs from BPI challenges 6 , rely on winner reports to identify the possible interventions (e.g., [35,37]). Continuous methods, on the other hand, focus on recommending the next task(s) (e.g., [15,6,47]) or resource allocation (e.g., [3,1,21]).…”

“…Predictions, however, only become useful to users when they are combined with recommendations [28]. In this setting, prescriptive process monitoring is a family of methods to recommend interventions during the execution of a case that, if followed, optimize the process with respect to one or more performance indicators [35]. For instance, an intervention might improve the probability of the desired outcome (e.g.…”