Deep Learning and Transfer Learning Architectures for English Premier League Player Performance Forecasting

TL;DR

The paper tackles EPL player performance forecasting by comparing Ridge regression, LightGBM, and a 1D CNN across four player positions, with an additional transfer-learning exploration using The Guardian news corpus. The CNN consistently outperforms baselines on holdout data and yields the strongest Spearman-based ranking signals, establishing a new performance standard for EPL forecasting models. Transfer learning from news signals provides limited or no improvement, highlighting the challenge of integrating textual data for fine-grained player-level predictions. The work underscores the CNN approach as a robust foundation for FPL AI agents and points to future avenues in ranking-optimized objectives and richer, multi-source transfer learning.

Abstract

This paper presents a groundbreaking model for forecasting English Premier League (EPL) player performance using convolutional neural networks (CNNs). We evaluate Ridge regression, LightGBM and CNNs on the task of predicting upcoming player FPL score based on historical FPL data over the previous weeks. Our baseline models, Ridge regression and LightGBM, achieve solid performance and emphasize the importance of recent FPL points, influence, creativity, threat, and playtime in predicting EPL player performances. Our optimal CNN architecture achieves better performance with fewer input features and even outperforms the best previous EPL player performance forecasting models in the literature. The optimal CNN architecture also achieves very strong Spearman correlation with player rankings, indicating its strong implications for supporting the development of FPL artificial intelligence (AI) Agents and providing analysis for FPL managers. We additionally perform transfer learning experiments on soccer news data collected from The Guardian, for the same task of predicting upcoming player score, but do not identify a strong predictive signal in natural language news texts, achieving worse performance compared to both the CNN and baseline models. Overall, our CNN-based approach marks a significant advancement in EPL player performance forecasting and lays the foundation for transfer learning to other EPL prediction tasks such as win-loss odds for sports betting and the development of cutting-edge FPL AI Agents.

Figures (15)

• Figure 1: High-Level Data Scraping and Cleaning Pipeline.
• Figure 2: Expansion of Data Pipeline for Transfer Learning per Position.
• Figure 3: Custom CNN Architecture for FPL Performance Forecasting.
• Figure 4: LightGBM feature importance measured by the percentage of splits performed with a given feature.
• Figure 5: 2D Histogram on the average performance of LightGBM during CV for each combination in the hyperparameter grid.