The thesis proposes a stock price prediction model based on a Dynamic Graph Neural Network (DGNN), which represents stocks and their interactions through daily events, enriched by sequential models (GRU, Transformer, and MAMBA) for predicting the next day's closing price. The dataset includes stock data, macroeconomic data, and news, pre-processed to build a dynamic graph. The experimental results demonstrate the model's effectiveness in capturing market dynamics and predicting prices.