From Weak Signals to Risk Indicators : An LLM-Based Information Extraction Architecture for IT Project Risk Management

Title data

Paetzold, Felix ; Guggenberger, Tobias ; Jungk, Tim ; Protschky, Dominik ; Strüker, Jens:
From Weak Signals to Risk Indicators : An LLM-Based Information Extraction Architecture for IT Project Risk Management.
In: Electronic Markets. Vol. 36 (2026) . - 76.
ISSN 1422-8890
DOI: https://doi.org/10.1007/s12525-026-00928-6

Project information

Abstract in another language

Effective risk management is crucial yet challenging in modern projects because early warning signals often surface in informal, unstructured data sources and evolve as project contexts change. Since prevailing Project Risk Management (PRM) practices largely depend on structured inputs and episodic control routines, they can miss these subtle signals, creating a temporal detection gap between risk emergence and formal identification. This paper introduces an LLM-based architecture for Information Extraction in PRM. Following a Design Science Research approach, we design, instantiate, and evaluate an architecture governed by two complementary flows: an Information Flow that continuously transforms heterogeneous project communication into structured, evidence-linked risk indicators through domain-specialized extraction and cross-source reconciliation, and an Extraction Control Flow that externalizes and versions extraction behavior to remain adaptable, transparent, and auditable. We further abstract four nascent design principles encapsulating transferable design knowledge for auditable and adaptable LLM-based information extraction in dynamic, context-rich domains.