With recent advancements in deep learning and the availability of huge amount of data, data-driven prediction in time series has attracted more and more attention. Specifically, traffic forecasting is the key component of a transportation system powered by artificial intelligence[2] [5]. Traditionally, time series forecasting includes methods such as K-nearest Neighbor (KNN), Support Vector Regression (SVR), etc [6]. This paper proposes the stacked LSTM model to capture the complex temporal patterns. The main contributions include: - Analyzing real traffic volume data in Toronto downtown area - Proposing the stacked LSTM model with substantial gain comparing to the baseline model - Improving the model performance with a comprehensive set of training methodologies Deep learning has been widely adopted in time series forecasting[5]. One category is time series classification which assigns predefined class labels to time series output.