Transforming Unstructured Corporate Documents into Queryable Knowledge Bases via Data Mining and Large Language Models
Nicel Bilimler Dergisi · 29.06.2026 · 8 (1) · 100-117
DOI: 10.51541/nicel.1932954 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nicel Bilimler Dergisi, online erschienen am 29.06.2026. Verfasst von Ali Sarıtaş und 2 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben.
Abstract (Originalsprache)
Unstructured corporate documents, such as invoices and inventory reports, pose significant challenges for automated data extraction and analysis. This study proposes an end-to-end framework that transforms text-based PDF documents into highly structured CSV datasets using domain-specific regular expressions (regex) and data mining techniques, bypassing the need for optical character recognition (OCR). To validate the analytical consistency of the extracted data, descriptive statistical analyses, feature engineering, and customer segmentation were performed. Subsequently, the structured datasets were utilized as knowledge bases for five distinct large language models (LLMs), including GPT-5, Gemini 2.5, Grok 4, Qwen3-Max, and DeepSeek-V3.1 to evaluate their natural language query performance. A comparative analysis based on concrete question-answering scenarios revealed that while well-structured data significantly enhances LLM accuracy, overall performance is heavily constrained by the models' context length limits and multi-row reasoning capabilities. GPT-5 and Gemini 2.5 achieved the highest success rates. Ultimately, the findings demonstrate that coupling traditional data mining techniques with generative AI provides a highly reliable approach for transforming unstructured corporate documents into queryable decision-support systems.
Zitieren
APA
Sarıtaş, A., Kaya, İ., & Günal, E. Ş. (2026). Transforming Unstructured Corporate Documents into Queryable Knowledge Bases via Data Mining and Large Language Models. Nicel Bilimler Dergisi, 8(1), 100-117. https://doi.org/10.51541/nicel.1932954
Vancouver
Sarıtaş A, Kaya İ, Günal EŞ. Transforming Unstructured Corporate Documents into Queryable Knowledge Bases via Data Mining and Large Language Models. Nicel Bilimler Dergisi. 2026;8(1):100-117. doi:10.51541/nicel.1932954
BibTeX
@article{Sarta2026,
author = {Sarıtaş, Ali and Kaya, İlknur and Günal, Efnan Şora},
title = {Transforming Unstructured Corporate Documents into Queryable Knowledge Bases via Data Mining and Large Language Models},
journal = {Nicel Bilimler Dergisi},
year = {2026},
volume = {8},
number = {1},
pages = {100--117},
doi = {10.51541/nicel.1932954}
}
EUVIMED