A Software Library for Conducting Large Scale Experiments on Learning to Rank Algorithms

‘is paper presents an ecient application for driving large scale experiments on Learning to Rank (LtR) algorithms. We designed a so‰ware library that exploits caching mechanisms and ecient data structures to make the execution of massime experiments on LtR algorithms as fast as possible in order to try as many combinations of components as possible. ‘is presented so‰ware has been tested on di‚erent algorithms as well as on di‚erent implementations of the same algorithm in di‚erent libraries. ‘is so‰ware is highly con€gurable and extensible in order to enable the seamless addition of new features, algorithms, and libraries.