A Genetic Algorithm for Optimizing Fantasy Football Trades with Playoff Biasing

TL;DR

This work addresses automated trade generation in fantasy football by formulating a playoff-weighted, multi-objective optimization problem solved via a genetic algorithm. The method evolves complex, multi-player trades using custom mutations and elitism, integrating real-time ESPN projections across all positions. Empirical results in a 12-team ESPN league (Week 8, 2025) show the GA identifying trades with negative costs and positive gains for both sides, with playoff bias enabling strategic late-season roster improvements. The framework is open-source and extensible to other sports or combinatorial optimization tasks requiring temporal biasing and opponent-aware negotiation dynamics.

Abstract

Fantasy football leagues involve strategic player trades to optimize team performance. However, identifying optimal trades is complex due to varying player projections, positional needs, and league-specific scoring. Existing approaches focus on team selection or lineup optimization, but automated trade generation remains underexplored. In this paper, an algorithm that generates optimal trades, biasing toward improved playoff performance while maintaining apparent fairness for negotiation is explored. We introduce a genetic algorithm for fantasy football trade optimization, building on existing frameworks for team selection and lineup generation. The algorithm initializes with single-player trades, evolves through custom mutations (add/remove players, combine trades, exchange players, add from other trades, and spawn new trades), and uses team-specific elitism to preserve diversity. The cost function incorporates a playoff-weighted gain for the user's team (while maintaining apparent fairness), opponent gain, and fairness penalty. Integration with ESPN data sources enables real-time projections for all positions, including kickers and defenses. On a 12-team ESPN league (Week 8, 2025), the algorithm generated trades that upgraded the projected point totals of both the trade initiator and trade partner by nearly 3 fantasy points per week ensuring positive gains for both teams. The algorithm demonstrates effective trade optimization, with potential extensions to other fantasy sports or combinatorial problems requiring temporal biasing. Open-source implementation enables practical use and further research.