In recent years, advanced machine learning (ML) models have revolutionized industries ranging from the healthcare sector to retail and E-commerce. However, these models have become increasingly complex, making it difficult for even domain experts to understand and retrace the model's decision-making process. To address this challenge, several frameworks for explainable AI have been proposed and developed. This thesis focuses on counterfactual explanations (CFEs), which provide actionable insights by informing users how to modify inputs to achieve desired outputs. However, computing CFEs for a general black-box ML model is computationally expensive since it hinges on solving a challenging optimization problem. To efficiently solve this optimization problem, we propose using Bayesian optimization (BO), and introduce the novel algorithm Separated Bayesian Optimization (SBO). SBO exploits the formulation of the counterfactual function as a composite function. Additionally, we propose warm-starting SBO, which addresses the computational challenges associated with computing multiple CFEs. By decoupling the generation of a surrogate model for the black-box model and the computation of specific CFEs, warm-starting SBO allows us to reuse previous data and computations, resulting in computational discounts and improved efficiency for large-scale applications. Through numerical experiments, we demonstrate that BO is a viable optimization scheme for computing CFEs for black-box ML models. BO achieves computational efficiency while maintaining good accuracy. SBO improves upon this by requiring fewer evaluations while achieving accuracies comparable to the best conventional optimizer tested. Both BO and SBO exhibit improved capabilities in handling various classes of ML decision models compared to the tested baseline optimizers. Finally, Warm-starting SBO significantly enhances the performance of SBO, reducing function evaluations and errors when computing multiple sequential CFEs. The results indicate a strong potential for large-scale industry applications. / Avancerade maskininlärningsmodeller (ML-modeller) har på senaste åren haft stora framgångar inom flera delar av näringslivet, med allt ifrån hälso- och sjukvårdssektorn till detaljhandel och e-handel. I jämn takt med denna utveckling har det dock även kommit en ökad komplexitet av dessa ML-modeller vilket nu lett till att även domänexperter har svårigheter med att förstå och tolka modellernas beslutsprocesser. För att bemöta detta problem har flertalet förklarbar AI ramverk utvecklats. Denna avhandling fokuserar på kontrafaktuella förklaringar (CFEs). Detta är en förklaringstyp som anger för användaren hur denne bör modifiera sin indata för att uppnå ett visst modellbeslut. För en generell svarta-låda ML-modell är dock beräkningsmässigt kostsamt att beräkna CFEs då det krävs att man löser ett utmanande optimeringsproblem. För att lösa optimeringsproblemet föreslår vi användningen av Bayesiansk Optimering (BO), samt presenterar den nya algoritmen Separated Bayesian Optimization (SBO). SBO utnyttjar kompositionsformuleringen av den kontrafaktuella funktionen. Vidare, utforskar vi beräkningen av flera sekventiella CFEs för vilket vi presenterar varm-startad SBO. Varm-startad SBO lyckas återanvända data samt beräkningar från tidigare CFEs tack vare en separation av surrogat-modellen för svarta-låda ML-modellen och beräkningen av enskilda CFEs. Denna egenskap leder till en minskad beräkningskostnad samt ökad effektivitet för storskaliga tillämpningar.  I de genomförda experimenten visar vi att BO är en lämplig optimeringsmetod för att beräkna CFEs för svarta-låda ML-modeller tack vare en god beräknings effektivitet kombinerat med hög noggrannhet. SBO presterade ännu bättre med i snitt färre funktionsutvärderingar och med fel nivåer jämförbara med den bästa testade konventionella optimeringsmetoden. Både BO och SBO visade på bättre kapacitet att hantera olika klasser av ML-modeller än de andra testade metoderna. Slutligen observerade vi att varm-startad SBO gav ytterligare prestandaökningar med både minskade funktionsutvärderingar och fel när flera CFEs beräknades. Dessa resultat pekar på stor potential för storskaliga tillämpningar inom näringslivet.

This master’s thesis in ethnology aim to enlighten the driving forces behind why a local football club, in a segregated residential area, outside of Stockholm in Sweden, chooses to develop its association in a more social direction. This is a cultural study of why football, as a cultural phenomenon, is expected to be able to solve social problems, and more generally how is sport considered a tool and a solution to social problems? Why is football expected to be able to solve segregation in a socio-economically vulnerable areas, of those who lead the sports activities? The empirical material of this essay has been collected through oral interviews from leaders of the association and government officials. Material from the association's development documents, state active board members from the association, government documents, and news articles have also been analyzed. By using the Political Discourse Theory by Ernesto Laclau and Chantal Mouffe (2008 [1985]), the situations for how the sports activities have been designed can be seen as made in relation to the general hegemonic discourse on the social benefits of sport. It is also possible to discover how government grants work as guidelines and point out what the sports movement should perform under state supervision. Logics of Critical Explanation in Social and Political Theory (2007), by Jason Glynos and David Howarth, are used in the analysis and especially their fantasmatic logic has given this study an insight into the idea or perception that football leaders have of the outside world, in this case the idea of the social benefit of sport. Which in turn can explain why they in turn invest their commitment in and attract their drive from these ideas because the conviction is about being able to change the socio-economic situation in their local area. In the end, however, it turns out that neither sport nor football alone cannot serve as the solution in the fight against child poverty, criminal activity, and segregation. Sport’s simply does not have all the characteristics required to reform, challenge, or question a social order created or even built on inequality and segregation. But this in no way takes sport into account in contexts where it can socially contribute to a community that can play a significant role for its participants in their everyday lives.