Automated Financial Report Summarization Using Python: A PDF-Based Approach

Abstract

Financial reports are often lengthy, complex, and filled with domain-specific jargon, making it
difficult for analysts and stakeholders to extract key insights efficiently. This study proposes an
automated summarization system using Natural Language Processing (NLP) techniques to generate
concise and coherent summaries of financial reports. The system employs a two-stage summarization
architecture combining extractive and abstractive methods based on Transformer models such as
BART, PEGASUS, and T5. Evaluation on simulated financial document datasets demonstrates that
the hybrid two-stage model achieves the highest ROUGE scores and information retention rates
compared to single-model baselines. The results indicate that NLP-driven summarization can
significantly reduce analysts’ workload and improve financial decision-making speed