FINANCIAL SENTIMENT ANALYSIS USING REAL TIME STRATEGIC DECISION-MAKING

Financial markets operate in environments characterized by high volatility, rapid information flow, and complex behavioural patterns. Traditional financial decision models, relying mainly on historical data and logical assumptions, often overlook psychological and sentiment-based influences that significantly impact market outcomes. In this landscape, financial sentiment analysis has become a valuable tool for gaining real-time insights into market sentiment and investor behaviour. This study explores how financial sentiment analysis can enhance strategic decision-making in dynamic settings. Utilizing behavioural finance and decision theory, a unified framework is developed that integrates real-time sentiment data into financial strategies. Data collection includes sources like financial news, analyst reports, social media platforms, and market indices. Advanced natural language processing, machine learning, and large language model (LLM) techniques are used to extract sentiment and incorporate it into predictive and optimization-based decision models. Designed to support portfolio management, risk assessment, and real-time investment decisions, the framework aims to improve agility and accuracy. The model's performance is evaluated against traditional decision-making methods using metrics such as predictive accuracy, decision speed, and risk-adjusted returns. Results suggest that sentiment-based models significantly enhance adaptability, responsiveness, and decision quality. This research bridges behavioral finance with AI analytics, offering practical insights for investors, fund managers, and policymakers seeking stronger strategies in volatile markets.