Rugby-Bot: Utilizing Multi-Task Learning & Fine-Grained Features for Rugby League Analysis

TL;DR

This paper introduces Rugby-Bot, a multi-task learning system that uses fine-grained spatial data and a wide-and-deep approach to generate consistent, multi-faceted predictions for Rugby League analysis, including distributional outputs.

Contribution

The paper presents a novel multi-task learning framework with fine-grain spatial features and distribution prediction capabilities for sports analysis, specifically applied to Rugby League.

Findings

Effective multi-task predictions from a single source

Utilizes fine-grain spatial data for improved accuracy

Predicts distributions instead of single point estimates

Abstract

Sporting events are extremely complex and require a multitude of metrics to accurate describe the event. When making multiple predictions, one should make them from a single source to keep consistency across the predictions. We present a multi-task learning method of generating multiple predictions for analysis via a single prediction source. To enable this approach, we utilize a fine-grain representation using fine-grain spatial data using a wide-and-deep learning approach. Additionally, our approach can predict distributions rather than single point values. We highlighted the utility of our approach on the sport of Rugby League and call our prediction engine "Rugby-Bot".