Original title: A systematic Approach to constructing a Chance-and-Risk Matrix for Semiconductor Supply Chains
Ema Salkić, Alexander Fichtl, Philipp Ulrich, Hans Ehm +2 · September 2026
Computer chip supply chains face major threats from politics, factory locations, and fast-changing technology. Right now, no automated tool continuously pulls and organizes risk clues from public company reports. Researchers built a system to solve this. The tool gathers company documents and uses large language models, which are smart text-reading programs, to spot risks and opportunities. It connects these points in an organized web of data, combines duplicates, and scores their importance. A formula, a language model, and human experts help rank each item. Tested on five chip firms, it created 76,207 scored items, with 92.6% verified as valid. The final charts revealed that government trade restrictions are the biggest risk shared across the companies.
Suppose you're organizing a large fundraiser and receive numerous reports from volunteers about potential problems, each written in their own style. It's difficult to compile a complete list because some risks are mentioned multiple times or in vague terms. In this paper, the system acts like a coordinator who reads all reports, extracts key issues, removes duplicates, and ranks them by importance using computer analysis, AI insights, and volunteer feedback. This ensures the most critical problems get addressed first.
This system helps semiconductor companies and policymakers prioritize risks in their supply chains, which can prevent disruptions affecting electronics production worldwide. By automating risk extraction, it saves time and improves the accuracy of threat assessments.
The abstract doesn't specify limitations, but the system is tested on only five companies, which may limit its generalizability. It relies on public disclosures, which might not capture internal or confidential risks.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
A systematic Approach to constructing a Chance-and-Risk Matrix for Semiconductor Supply Chains — Ema Salkić, Alexander Fichtl, Philipp Ulrich et al.
Abstract licence: CC0
Explanation generated by Synthesis from the abstract — it is not the original paper. This is a preprint, so it hasn't necessarily been peer reviewed.