Personalized Chain-of-Thought Summarization of Financial News for Investor Decision Support

2025-10-24

AI Summary

Financial news overload obscures critical market signals with noise, impairing investor decision-making efficiency. To address this, we propose P-Chain, a personalized chain-of-thought summarization framework that guides large language models (LLMs) through event-driven, keyword-conditioned reasoning to generate investment-relevant summaries end-to-end from raw news. P-Chain integrates prompt engineering, fine-grained event extraction, and semantic keyword matching to construct an interpretable inference path: “news → event → investment insights.” Experimental results demonstrate that P-Chain significantly outperforms baseline methods in summary relevance (+12.6% ROUGE-L), event completeness, and investor comprehension (+31% in human evaluation), while effectively supporting downstream investment analysis tasks. This work establishes a novel paradigm for personalized financial text summarization grounded in explainable, user-guided reasoning.

Technology Category

• Natural Language Processing: Summarization
• Data Mining & Knowledge Management: Data Visualization & Summarization
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Financial advisors and investors struggle with information overload from financial news, where irrelevant content and noise obscure key market signals and hinder timely investment decisions. To address this, we propose a novel Chain-of-Thought (CoT) summarization framework that condenses financial news into concise, event-driven summaries. The framework integrates user-specified keywords to generate personalized outputs, ensuring that only the most relevant contexts are highlighted. These personalized summaries provide an intermediate layer that supports language models in producing investor-focused narratives, bridging the gap between raw news and actionable insights.

Problem

• Condensing financial news into concise event-driven summaries
• Integrating user keywords to generate personalized investment insights
• Bridging raw news and actionable insights for investors

Innovation

• Chain-of-Thought framework for financial news summarization
• User-specified keywords enable personalized summary generation
• Event-driven summaries bridge raw news to actionable insights