Accurate stock trend forecasting is a central challenge in financial economics due to the highly nonlinear and interdependent nature of market dynamics. Traditional statistical and machine learning models often fall short in modeling complex temporal dependencies and interstock relationships. This paper proposes a novel framework based on graph neural networks for short-term stock trend prediction. By representing sliding windows of historical stock prices as temporal graphs and incorporating domain-specific technical indicators – namely, the 5-day moving average and the 14-day relative strength index – the proposed model captures both local temporal interactions and indicator-informed momentum patterns. Experimental results highlight the potential of graph-based modeling in capturing short-term trading signals and improving the predictive performance of financial forecasting systems.