Leveraging Synthetically Generated Data for Real Estate Document Classification
Leveraging Synthetically Generated Data for Real Estate Document Classification
View/Date of Publication
12.2025Publisher
IEEE, Institute of Electrical and Electronics EngineersPublisher Location
New York, NYMetadata
Show full item record
Citable Links 
Abstract
Document classification in regulated domains like law, finance, or real estate is hindered by the scarcity of labeled data and strict privacy constraints. This paper presents a pipeline for synthetically generating training data for document classifiers using a combination of domain-specific templates, large language models, and data augmentation techniques. Focusing on two key document types relevant to real estate workflows, Child Support Certificate and Refurbishment Roadmap, we construct realistic multi-page documents and generate negative classes using LLM-generated distractors. We train a BERT-based classifier on this synthetic dataset and evaluate it on real-world OCR-extracted documents, achieving strong performance despite the absence of real documents in training. Our findings highlight the feasibility of using synthetic data to overcome annotation bottlenecks and pave the way for broader applications in privacy-sensitive industries.
Note
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.Subjects
Document Classification, Synthetic Data, Large Language Models, Natural Language Processing, Finance, Machine Learning
Classification (DDC)
004 InformatikFirst Publication
https://doi.org/10.1109/BigData66926.2025.11400789Conference
2025 IEEE International Conference on Big Data (BigData)Deußer, Tobias; Ramien, Gregor; Weber, Nico; Meidinger, Maximilian; Hahnbück, Max; Bauckhage, Christian; Sifa, Rafet: Leveraging Synthetically Generated Data for Real Estate Document Classification. New York, NY: IEEE, Institute of Electrical and Electronics Engineers, 2025.
Online-Ausgabe in bonndoc: https://doi.org/10.48565/bonndoc-809
Online-Ausgabe in bonndoc: https://doi.org/10.48565/bonndoc-809
@proceedings{handle:20.500.11811/13972,
doi: https://doi.org/10.48565/bonndoc-809,
author = {{Tobias Deußer} and {Gregor Ramien} and {Nico Weber} and {Maximilian Meidinger} and {Max Hahnbück} and {Christian Bauckhage} and {Rafet Sifa}},
title = {Leveraging Synthetically Generated Data for Real Estate Document Classification},
publisher = {IEEE, Institute of Electrical and Electronics Engineers},
year = 2025,
month = dec,
note = {Document classification in regulated domains like law, finance, or real estate is hindered by the scarcity of labeled data and strict privacy constraints. This paper presents a pipeline for synthetically generating training data for document classifiers using a combination of domain-specific templates, large language models, and data augmentation techniques. Focusing on two key document types relevant to real estate workflows, Child Support Certificate and Refurbishment Roadmap, we construct realistic multi-page documents and generate negative classes using LLM-generated distractors. We train a BERT-based classifier on this synthetic dataset and evaluate it on real-world OCR-extracted documents, achieving strong performance despite the absence of real documents in training. Our findings highlight the feasibility of using synthetic data to overcome annotation bottlenecks and pave the way for broader applications in privacy-sensitive industries.},
url = {https://hdl.handle.net/20.500.11811/13972}
}
doi: https://doi.org/10.48565/bonndoc-809,
author = {{Tobias Deußer} and {Gregor Ramien} and {Nico Weber} and {Maximilian Meidinger} and {Max Hahnbück} and {Christian Bauckhage} and {Rafet Sifa}},
title = {Leveraging Synthetically Generated Data for Real Estate Document Classification},
publisher = {IEEE, Institute of Electrical and Electronics Engineers},
year = 2025,
month = dec,
note = {Document classification in regulated domains like law, finance, or real estate is hindered by the scarcity of labeled data and strict privacy constraints. This paper presents a pipeline for synthetically generating training data for document classifiers using a combination of domain-specific templates, large language models, and data augmentation techniques. Focusing on two key document types relevant to real estate workflows, Child Support Certificate and Refurbishment Roadmap, we construct realistic multi-page documents and generate negative classes using LLM-generated distractors. We train a BERT-based classifier on this synthetic dataset and evaluate it on real-world OCR-extracted documents, achieving strong performance despite the absence of real documents in training. Our findings highlight the feasibility of using synthetic data to overcome annotation bottlenecks and pave the way for broader applications in privacy-sensitive industries.},
url = {https://hdl.handle.net/20.500.11811/13972}
}
The following license files are associated with this item:
