DIVIDEND POLICY IMPACT ON MARKET VALUE

Abstract

Dividend policy plays a crucial role in determining a firm's financial strategy and directly influences investor sentiment and market valuation. Traditionally, the relationship between dividend announcements and stock price behavior has been analyzed using econometric models and financial ratio analysis. However, these conventional approaches often fall short in capturing complex, nonlinear dependencies between dividend-related variables and market outcomes. In this study, we apply advanced Machine Learning (ML) and Deep Learning (DL) techniques to explore and predict the impact of dividend policy on the market value of publicly listed companies.The project involves collecting historical data on dividends, earnings per share, payout ratios, stock prices, and other financial indicators for a diverse set of firms across multiple sectors. ML models such as Random Forest, Support Vector Machine (SVM), and Gradient Boosting are used to identify key patterns and assess the predictive importance of dividend variables. Additionally, a Long Short-Term Memory (LSTM) network—a Deep Learning model particularly suited for time-series data—is employed to capture temporal dependencies and forecast future stock price movements post-dividend announcements.The results demonstrate that ML and DL techniques significantly outperform traditional statistical models in terms of prediction accuracy and insights generation. Particularly, LSTM models reveal delayed effects of dividend policy changes on market value, offering a more dynamic perspective. This research highlights the potential of AI-driven models in financial analysis and decision-making, providing valuable tools for investors, analysts, and corporate managers aiming to optimize dividend strategies for enhanced shareholder value.