Back-end of Kairos: A Prescriptive Process Monitoring Tool

Abstract

Prescriptive process monitoring is an approach that aims to predict potential failures and provide recommendations to optimize business processes. It seeks to improve efficiency and productivity by aiding enterprises in making informed decisions during process execution. For example, it can be applied to optimize a company’s supply chain management by predicting delays and suggesting actions based on historical data. The primary problem that this thesis address is the absence of a comprehensive tool capable of analyzing data from different sources and offering various types of prescriptive recommendations. Consequently, the objective of this study is to propose and implement a software solution that enables the integration of diverse algorithms and plugins in a seamless manner. The proposed approach includes back-end software that provides APIs to implement prescriptive process monitoring features. Users can upload event logs to the tool and receive various prescriptions for ongoing cases, encompassing predictions of the next activities, scoring the likelihood of adverse outcomes, providing treatment effects, and allocating resources based on treatment gains. Moreover, the modular design enhances adaptability and flexibility across various business domains. To evaluate the effectiveness of the proposed solution, a combination of requirements fulfillment evaluation and performance evaluation is conducted using datasets from the Business Process Intelligence Challenge (BPIC). As a result, this thesis contributes to the field by providing a prescriptive process monitoring tool that can provide multiple types of prescriptive recommendations.