Pricing Football Players using Neural Networks
This work addresses pricing in sports analytics, specifically for football simulation games, but is incremental as it applies standard neural network methods to a new dataset.
The paper tackled the problem of predicting football player prices using neural networks, achieving a top-5 accuracy of 87.2% among 119 categories and an average error of 6.32% from actual prices.
We designed a multilayer perceptron neural network to predict the price of a football (soccer) player using data on more than 15,000 players from the football simulation video game FIFA 2017. The network was optimized by experimenting with different activation functions, number of neurons and layers, learning rate and its decay, Nesterov momentum based stochastic gradient descent, L2 regularization, and early stopping. Simultaneous exploration of various aspects of neural network training is performed and their trade-offs are investigated. Our final model achieves a top-5 accuracy of 87.2% among 119 pricing categories, and places any footballer within 6.32% of his actual price on average.