🤖 AI Summary
Event prediction research has long suffered from domain fragmentation and terminological heterogeneity, impeding method reuse and knowledge transfer. To address this, we propose the first system-level model for event prediction, establishing a unified framework grounded in systems engineering principles. This framework formally characterizes the mapping from historical to future events and supports goal-state-oriented intervention decisions. Through cross-domain literature review, requirements modeling, and methodology assessment, we elicit functional and non-functional requirements and identify common challenges. We then introduce a reusable reference architecture, conduct a structured evaluation of state-of-the-art approaches, distill five open challenges, and formulate an actionable research roadmap. Our core contribution lies in the first systematic abstraction of event prediction at the system level and the cross-paradigm integration of diverse methodologies—enabling principled interoperability, scalability, and extensibility across domains and application scenarios.
📝 Abstract
Event prediction is the ability of anticipating future events, i.e., future real-world occurrences, and aims to support the user in deciding on actions that change future events towards a desired state. An event prediction method learns the relation between features of past events and future events. It is applied to newly observed events to predict corresponding future events that are evaluated with respect to the user’s desired future state. If the predicted future events do not comply with this state, actions are taken towards achieving desirable future states. Evidently, event prediction is valuable in many application domains such as business and natural disasters. The diversity of application domains results in a diverse range of methods that are scattered across various research areas which, in turn, use different terminology for event prediction methods. Consequently, sharing methods and knowledge for developing future event prediction methods is restricted. To facilitate knowledge sharing on account of a comprehensive integration and assessment of event prediction methods, we take a systems perspective to integrate event prediction methods into a single system, elicit requirements, and assess existing work with respect to the requirements. Based on the assessment, we identify open challenges and discuss future research directions.
