ericcolon/TennisPrediction-2

This project proposes a novel approach for tennis modeling by introducing stacking, an ensemble learning technique used to combine information from multiple predictive models to generate a new model, a so called super learner. A historical dataset of 101295 ATP tennis matches played between 2004-2014 is used to train the meta-model.

TennisPrediction

This project proposes a novel approach for tennis modeling by introducing stacking, an ensemble learning technique used to combine information from multiple predictive models to generate a new model, a so called super learner. A historical dataset of 101295 ATP tennis matches played between 2004-2014 is used to train the meta-model.

https://github.com/akozlu/TennisPrediction/blob/master/thesis.pdf