Fantasy Football
Fantasy sports, like fantasy football, involve creating virtual teams based on real-world athlete performance to compete against others, aiming to maximize points within constraints like salary caps. Current research focuses on improving team selection strategies using advanced machine learning techniques, including transformer models and ensemble methods, to predict player performance and optimize lineup construction via algorithms such as linear programming and knapsack algorithms. These advancements enhance the user experience and provide insights into user behavior, such as spending propensity and the impact of upselling strategies, while also addressing platform challenges like detecting fraudulent activity through graph-based solutions.
Papers
Deep Artificial Intelligence for Fantasy Football Language Understanding
Aaron Baughman, Micah Forester, Jeff Powell, Eduardo Morales, Shaun McPartlin, Daniel Bohm
Large Scale Diverse Combinatorial Optimization: ESPN Fantasy Football Player Trades
Aaron Baughman, Daniel Bohm, Micah Forster, Eduardo Morales, Jeff Powell, Shaun McPartlin, Raja Hebbar, Kavitha Yogaraj, Yoshika Chhabra, Sudeep Ghosh, Rukhsan Ul Haq, Arjun Kashyap