Leveraging Synthetically Generated Data for Real Estate Document Classification
Authors:
- 8 December 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7253-7257
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 LLMgenerated 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.Keywords
Funding Information
- Ministry of Education
This publication has 27 references indexed in Scilit:
- On the Generation of Synthetic Invoices for Training Machine Learning ModelsIEEE Access, 2025
- Opportunities and Challenges of Generative-AI in Finance2024
- Informed Named Entity Recognition Decoding for Generative Language Models2024
- Reinforcement prompting for financial synthetic data generationThe Journal of Finance and Data Science, 2024
- Artificial intelligence co-piloted auditingInternational Journal of Accounting Information Systems, 2024
- Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models2023
- Uncovering Inconsistencies and Contradictions in Financial Reports using Large Language Models2023
- Deep learning for detecting financial statement fraudDecision Support Systems, 2020
- Deep learning for financial sentiment analysis on finance news providers2016
- Credit Risk Assessment Using Statistical and Machine Learning: Basic Methodology and Risk Modeling ApplicationsComputational Economics, 2000