Odendaal, Coenraad Lukas (2025) Decision-Making Under Pressure: A Multi-Level Analysis of Tactical Adaptation and Passing Intelligence in Football. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (20MB) | Preview |
Abstract
In professional football, decisions about substitutions can have a significant impact on games and are usually made under pressure and with very little time. As of yet, most current analytics frameworks remain mostly descriptive and retrospective. This study proposes a combination of three models for the detection of player performance using the Ghost Opportunity Index (GOI) for decision-making quality, the Formation Drift Index (FDI) for any structural changes, and the High Pressure Expected Impact (HPEI) for player performance. Using open-source StatsBomb event data from FC Barcelona's La Liga games, these indicators were combined into a deterministic, easy-to-understand substitution engine that was tested through time-series and player-level analysis. This model alerts managers on average 11 minutes earlier than the current substitution methods, making real-time substitution decisions more effective. The results demonstrate that GOI and FDI go up during the last few minutes of a game, indicating that decision quality declines while tactical stability increases. HPEI also successfully separates players who can handle pressure from those who cannot. The study shows that it is possible to make interpretable, prescriptive substitution decisions using only event data. Full testing of the model was limited by missing lineup data and fatigue indicators.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Hasanuzzaman, Mohammed UNSPECIFIED |
| Uncontrolled Keywords: | Football analytics; Substitution decision support; Expected Threat (xT); Tactical drift; Performance under pressure; Ghost Opportunity Index |
| Subjects: | G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports > Soccer Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 08 Sep 2026 11:00 |
| Last Modified: | 08 Sep 2026 11:00 |
| URI: | https://norma.ncirl.ie/id/eprint/9890 |
Actions (login required)
![]() |
View Item |
Tools
Tools