# What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data

arXiv: https://arxiv.org/abs/2106.01786 · HTML: https://mlsanity.com/paper/2106.01786/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 33 references that are in the map.
- First posted on arXiv 3 Jun 2021.

## Builds on (most cited first, 3 of 3)

- [Actions Speak Louder Than Goals: Valuing Player Actions in Soccer](https://mlsanity.com/paper/1802.07127/) (2018)
- [Optimising Game Tactics for Football](https://mlsanity.com/paper/2003.10294/) (2020)
- [Leveraging Statistical Multi-Agent Online Planning with Emergent Value Function Approximation](https://mlsanity.com/paper/1804.06311/) (2018)

## Built on by (most cited first, 10 of 10)

- [ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton](https://mlsanity.com/paper/2112.01044/) (2021)
- [Benchmarking Stroke Forecasting with Stroke-Level Badminton Dataset](https://mlsanity.com/paper/2306.15664/) (2023)
- [About latent roles in forecasting players in team sports](https://mlsanity.com/paper/2304.08272/) (2023)
- [Action Valuation in Sports: A Survey](https://mlsanity.com/paper/2504.06163/) (2025)
- [Better Prevent than Tackle: Valuing Defense in Soccer Based on Graph Neural Networks](https://mlsanity.com/paper/2512.10355/) (2025)
- [PGD: A Large-scale Professional Go Dataset for Data-driven Analytics](https://mlsanity.com/paper/2205.00254/) (2022)
- [A Machine Learning Framework for Off Ball Defensive Role and Performance Evaluation in Football](https://mlsanity.com/paper/2601.00748/) (2026)
- [FeatureBox: Feature Engineering on GPUs for Massive-Scale Ads Systems](https://mlsanity.com/paper/2210.07768/) (2022)
- [The ProfessionAl Go annotation datasEt (PAGE)](https://mlsanity.com/paper/2211.01559/) (2022)
- [A Universal Dense Football Event Representation Based on TabTransformer](https://mlsanity.com/paper/2606.09327/) (2026)

## Abstract (arXiv)

Objectively quantifying the value of player actions in football (soccer) is a challenging problem. To date, studies in football analytics have mainly focused on the attacking side of the game, while there has been less work on event-driven metrics for valuing defensive actions (e.g., tackles and interceptions). Therefore in this paper, we use deep learning techniques to define a novel metric that values such defensive actions by studying the threat of passages of play that preceded them. By doing so, we are able to value defensive actions based on what they prevented from happening in the game. Our Defensive Action Expected Threat (DAxT) model has been validated using real-world event-data from the 2017/2018 and 2018/2019 English Premier League seasons, and we combine our model outputs with additional features to derive an overall rating of defensive ability for players. Overall, we find that our model is able to predict the impact of defensive actions allowing us to better value defenders using event-data.