As urbanization intensifies, the ability to accurately predict short-term road traffic patterns has become a paramount aspect of efficient urban infrastructure management. This work proposes a Long-Short Term Memory (LSTM)-based approach to predict urban traffic flow, by incorporating contextual factors like weather and holidays. The model leverages historical road traffic data from the Adelaide Councils, Australia. After evaluating different models, LSTM has shown superior ability in capturing traffic patterns and effectively forecasting traffic peaks. This study highlights the effectiveness of the proposed model in catching temporal dependencies in traffic data, paving the way for improved service planning and resource allocation in dynamic urban environments.