Multi-Criteria Financial Screening Under Data Uncertainty: An LLM-Extraction and Min–Max TOPSIS Approach for SMEs
Open Access
- 20 June 2026
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 14 (12) , 2217
Abstract
Small and medium enterprises routinely face a paradox in financial monitoring: their accounting documents exist, but the cost of converting heterogeneous PDFs into timely financial signals is prohibitive without dedicated analytical staff or specialized software. This paper presents a two-layer artifact, designed under Design Science Research, that bridges this gap using only public-web large language models (LLMs) and a parsimonious multi-criteria decision routine. Layer 1 implements a structured LLM-driven workflow that extracts account–value pairs from annual tax balance sheets without code, APIs, or fine-tuning. Layer 2 reconstructs auditable accounting aggregates and ranks yearly financial condition through TOPSIS with min–max normalization—a deliberate replacement for classical vector normalization, which fails when profitability indicators are negative, as routinely occurs in distress years. To avoid size effects and algebraic redundancy, the decision matrix uses only three criteria spanning liquidity, profitability, and solvency. The artifact is demonstrated in a four-year case study of an anonymized construction SME (2021–2024), with accountant-verified document-level match rates of 0.810, 0.998, 0.950, and 0.909. Equal weighting is the only weighting configuration used; a supplementary entropy-based dispersion diagnostic yields the same ordinal ranking—2024 > 2023 > 2021 > 2022—and 10,000 Monte Carlo replications, with uncertainty injected at the reconstructed-aggregate level, confirm that the extreme ranks are invariant across all runs. The contribution is methodological and practical: a transparent, low-infrastructure pipeline that brings first-pass financial screening within reach of SMEs operating under severe data and budget constraints.Keywords
Funding Information
- Pontificia Universidad Católica de Valparaíso (044.767/2026)
- Comisión Nacional de Investigación Científica y Tecnológica (3260068)
This publication has 22 references indexed in Scilit:
- Random normed k-means: A paradigm-shift in clustering within probabilistic metric spacesJournal of Computational Mathematics and Data Science, 2026
- Loot Crates2024
- Sustainability metrics and a hybrid decision-making model for selecting lean manufacturing toolsResources, Environment and Sustainability, 2023
- Dynamic assessment of project portfolio risks from the life cycle perspectiveComputers & Industrial Engineering, 2022
- A state-of the-art survey of TOPSIS applicationsExpert Systems with Applications, 2012
- A cost control system development: A collaborative approach for small and medium-sized contractorsInternational Journal of Project Management, 2009
- Cash Flow Forecasting Model for General Contractors Using Moving Weights of Cost CategoriesJournal of Management in Engineering, 2005
- Business failures in the construction industryEngineering, Construction and Architectural Management, 2000
- Financial Performance Analysis for Construction IndustryJournal of Construction Engineering and Management, 1992
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948