Applying Deep Bidirectional LSTM and Mixture Density Network for Basketball Trajectory Prediction
This work addresses the problem of costly manual data analytics for basketball teams by providing a tool to predict and generate shooting trajectories, though it is incremental as it combines existing methods for a specific domain.
The authors tackled basketball trajectory prediction by applying a deep bidirectional LSTM and mixture density network model, which outperformed other models in hit-or-miss classification accuracy and generated realistic trajectories in experiments on NBA SportVu data.
Data analytics helps basketball teams to create tactics. However, manual data collection and analytics are costly and ineffective. Therefore, we applied a deep bidirectional long short-term memory (BLSTM) and mixture density network (MDN) approach. This model is not only capable of predicting a basketball trajectory based on real data, but it also can generate new trajectory samples. It is an excellent application to help coaches and players decide when and where to shoot. Its structure is particularly suitable for dealing with time series problems. BLSTM receives forward and backward information at the same time, while stacking multiple BLSTMs further increases the learning ability of the model. Combined with BLSTMs, MDN is used to generate a multi-modal distribution of outputs. Thus, the proposed model can, in principle, represent arbitrary conditional probability distributions of output variables. We tested our model with two experiments on three-pointer datasets from NBA SportVu data. In the hit-or-miss classification experiment, the proposed model outperformed other models in terms of the convergence speed and accuracy. In the trajectory generation experiment, eight model-generated trajectories at a given time closely matched real trajectories.