Multi-Modal Trajectory Prediction of NBA Players

TL;DR

This paper introduces a multi-modal trajectory prediction method for NBA players using an LSTM architecture, which predicts multiple potential movements and their probabilities, outperforming existing models and capturing individual playing styles.

Contribution

It presents a novel multi-modal LSTM-based approach for predicting NBA player trajectories, incorporating a multi-modal loss function to improve realism and style learning.

Findings

Outperforms state-of-the-art trajectory prediction methods.

Generates more realistic and diverse player trajectories.

Learns individual player styles effectively.

Abstract

National Basketball Association (NBA) players are highly motivated and skilled experts that solve complex decision making problems at every time point during a game. As a step towards understanding how players make their decisions, we focus on their movement trajectories during games. We propose a method that captures the multi-modal behavior of players, where they might consider multiple trajectories and select the most advantageous one. The method is built on an LSTM-based architecture predicting multiple trajectories and their probabilities, trained by a multi-modal loss function that updates the best trajectories. Experiments on large, fine-grained NBA tracking data show that the proposed method outperforms the state-of-the-art. In addition, the results indicate that the approach generates more realistic trajectories and that it can learn individual playing styles of specific players.