Enhancing Business Analytics through Hybrid Summarization of Financial Reports

TL;DR

This paper introduces a hybrid summarization framework for financial reports and earnings calls, combining extractive and abstractive methods to produce concise, reliable summaries that balance performance and factual accuracy.

Contribution

It presents a novel two-stage hybrid summarization pipeline and evaluates long-range models alongside traditional methods for financial document summarization.

Findings

Long context models outperform traditional methods in overall performance.

Hybrid summarization achieves competitive results with better factual consistency.

Long-range models are effective in capturing contextual dependencies.

Abstract

Financial reports and earnings communications contain large volumes of structured and semi structured information, making detailed manual analysis inefficient. Earnings conference calls provide valuable evidence about a firm's performance, outlook, and strategic priorities. The manual analysis of lengthy call transcripts requires substantial effort and is susceptible to interpretive bias and unintentional error. In this work, we present a hybrid summarization framework that combines extractive and abstractive techniques to produce concise and factually reliable Reuters-style summaries from the ECTSum dataset. The proposed two stage pipeline first applies the LexRank algorithm to identify salient sentences, which are subsequently summarized using fine-tuned variants of BART and PEGASUS designed for resource constrained settings. In parallel, we fine-tune a Longformer Encoder-Decoder (LED) model to directly capture long-range contextual dependencies in financial documents. Model performance is evaluated using standard automatic metrics, including ROUGE, METEOR, MoverScore, and BERTScore, along with domain-specific variants such as SciBERTScore and FinBERTScore. To assess factual accuracy, we further employ entity-level measures based on source-precision and F1-target. The results highlight complementary trade offs between approaches, long context models yield the strongest overall performance, while the hybrid framework achieves competitive results with improved factual consistency under computational constraints. These findings support the development of practical summarization systems for efficiently distilling lengthy financial texts into usable business insights.