A systematic Approach to constructing a Chance-and-Risk Matrix for Semiconductor Supply Chains
2026-09-01 • Computation and Language
Computation and Language
AI summaryⓘ
The authors developed a system that automatically collects and analyzes public documents from semiconductor companies to find and score risks and opportunities mentioned in them. They use large language models to read the documents, organize the information into a connected map, remove duplicates, and rank the importance of each risk or opportunity. When tested on five companies, the system found mostly accurate results that matched experts’ opinions reasonably well. Their analysis showed that trade restrictions are a major shared risk for these companies. This work helps track complex supply chain risks without needing constant manual review.
semiconductor supply chainrisk intelligencelarge language modelsknowledge graphcorporate disclosurestrade restrictionsalgorithmic rankingexpert validationscored risk itemsSpearman correlation
Authors
Ema Salkić, Alexander Fichtl, Philipp Ulrich, Hans Ehm, Marta Bonik, Georg Groh
Abstract
Semiconductor supply chains face escalating risks from geopolitical tensions, geographic concentration, and rapid technological shifts, yet no scalable system continuously extracts, structures, and prioritizes risk intelligence from public corporate disclosures. We present an end-to-end pipeline that retrieves corporate documents for semiconductor companies and uses large language models (LLMs) to extract the risks and opportunities they describe. It organizes these into a knowledge graph linking each item to its category, sources, and related events, then merges duplicates and ranks them with a three-layer mechanism combining an algorithmic formula, an LLM relevance adjustment, and expert validation. Applied to five companies across the value chain, the pipeline produces 76,207 scored items, of which an independent check finds 92.6% valid. The automated rankings match expert judgment at an average Spearman correlation of 0.55 for risks and 0.72 for opportunities, and the resulting matrices identify trade restrictions as the dominant cross-company risk.